Merge branch 'main' into dev_apis

.gitignore

@@ -16,4 +16,5 @@ MaaS-lib
 .egg*
 dist
 build
-funasr.egg-info
+funasr.egg-info
+docs/_build

README.md

@@ -13,10 +13,10 @@
 | [**Highlights**](#highlights)
 | [**Installation**](#installation)
 | [**Docs**](https://alibaba-damo-academy.github.io/FunASR/en/index.html)
-| [**Tutorial**](https://github.com/alibaba-damo-academy/FunASR/wiki#funasr%E7%94%A8%E6%88%B7%E6%89%8B%E5%86%8C)
+| [**Tutorial_CN**](https://github.com/alibaba-damo-academy/FunASR/wiki#funasr%E7%94%A8%E6%88%B7%E6%89%8B%E5%86%8C)
 | [**Papers**](https://github.com/alibaba-damo-academy/FunASR#citations)
 | [**Runtime**](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime)
-| [**Model Zoo**](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/modelscope_models.md)
+| [**Model Zoo**](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md)
 | [**Contact**](#contact)
 | [**M2MET2.0 Challenge**](https://github.com/alibaba-damo-academy/FunASR#multi-channel-multi-party-meeting-transcription-20-m2met20-challenge)
 
@@ -28,7 +28,7 @@ For the release notes, please ref to [news](https://github.com/alibaba-damo-acad
 
 ## Highlights
 - FunASR supports speech recognition(ASR), Multi-talker ASR, Voice Activity Detection(VAD), Punctuation Restoration, Language Models, Speaker Verification and Speaker diarization.   
-- We have released large number of academic and industrial pretrained models on [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition)
+- We have released large number of academic and industrial pretrained models on [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition), ref to [Model Zoo](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md)
 - The pretrained model [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) obtains the best performance on many tasks in [SpeechIO leaderboard](https://github.com/SpeechColab/Leaderboard)
 - FunASR supplies a easy-to-use pipeline to finetune pretrained models from [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition)
 - Compared to [Espnet](https://github.com/espnet/espnet) framework, the training speed of large-scale datasets in FunASR is much faster owning to the optimized dataloader.
@@ -60,12 +60,8 @@ pip install -U modelscope
 # pip install -U modelscope -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple
 ```
 
-For more details, please ref to [installation](https://alibaba-damo-academy.github.io/FunASR/en/installation.html)
+For more details, please ref to [installation](https://alibaba-damo-academy.github.io/FunASR/en/installation/installation.html)
 
-[//]: # ()
-[//]: # (## Usage)
-
-[//]: # (For users who are new to FunASR and ModelScope, please refer to FunASR Docs([CN](https://alibaba-damo-academy.github.io/FunASR/cn/index.html) / [EN](https://alibaba-damo-academy.github.io/FunASR/en/index.html)))
 
 ## Contact
 

docs/README.md

@@ -0,0 +1,19 @@
+# FunASR document generation
+
+## Generate HTML
+For convenience, we provide users with the ability to generate local HTML manually.
+
+First, you should install the following packages, which is required for building HTML:
+```sh
+conda activate funasr
+pip install requests sphinx nbsphinx sphinx_markdown_tables sphinx_rtd_theme recommonmark
+```
+
+Then you can generate HTML manually.
+
+```sh
+cd docs
+make html
+```
+
+The generated files are all contained in the "FunASR/docs/_build" directory. You can access the FunASR documentation by simply opening the "html/index.html" file in your browser from this directory.

docs/index.rst

@@ -17,8 +17,8 @@ Overview
    :maxdepth: 1
    :caption: Installation
 
-   ./installation.md
-   ./docker.md
+   ./installation/installation.md
+   ./installation/docker.md
 
 .. toctree::
    :maxdepth: 1
@@ -44,6 +44,7 @@ Overview
    ./modelscope_pipeline/tp_pipeline.md
    ./modelscope_pipeline/sv_pipeline.md
    ./modelscope_pipeline/sd_pipeline.md
+   ./modelscope_pipeline/itn_pipeline.md
 
 .. toctree::
    :maxdepth: 1
@@ -56,8 +57,8 @@ Overview
    :maxdepth: 1
    :caption: Model Zoo
 
-   ./modelscope_models.md
-   ./huggingface_models.md
+   ./model_zoo/modelscope_models.md
+   ./model_zoo/huggingface_models.md
 
 .. toctree::
    :maxdepth: 1
@@ -70,6 +71,7 @@ Overview
    ./runtime/grpc_python.md
    ./runtime/grpc_cpp.md
    ./runtime/websocket_python.md
+   ./runtime/websocket_cpp.md
 
 .. toctree::
    :maxdepth: 1
@@ -84,25 +86,25 @@ Overview
    :maxdepth: 1
    :caption: Funasr Library
 
-   ./build_task.md
+   ./reference/build_task.md
 
 .. toctree::
    :maxdepth: 1
    :caption: Papers
 
-   ./papers.md
+   ./reference/papers.md
 
 .. toctree::
    :maxdepth: 1
    :caption: Application
 
-   ./application.md
+   ./reference/application.md
 
 .. toctree::
    :maxdepth: 1
    :caption: FQA
 
-   ./FQA.md
+   ./reference/FQA.md
 
 
 Indices and tables

docs/modelscope_models.md → docs/model_zoo/modelscope_models.md

@@ -15,7 +15,8 @@ Here we provided several pretrained models on different datasets. The details of
 | [Paraformer-large-long](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN  | Alibaba Speech Data (60000hours) |    8404    |   220M    |    Offline     | Which ould deal with arbitrary length input wav                                                                                 |
 | [Paraformer-large-contextual](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | CN & EN  | Alibaba Speech Data (60000hours) |    8404    |   220M    |    Offline     | Which supports the hotword customization based on the incentive enhancement, and improves the recall and precision of hotwords. |
 |              [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary)              | CN & EN  | Alibaba Speech Data (50000hours) |    8358    |    68M    |    Offline     | Duration of input wav <= 20s                                                                                                    |
-|          [Paraformer-online](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary)           | CN & EN  | Alibaba Speech Data (50000hours) |    8404    |    68M    |     Online     | Which could deal with streaming input                                                                                           |
+|           [Paraformer-online](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary)           | CN & EN  | Alibaba Speech Data (50000hours) |    8404    |    68M    |     Online     | Which could deal with streaming input                                                                                           |
+|  [Paraformer-large-online](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary)        | CN & EN  | Alibaba Speech Data (60000hours) |    8404    |   220M    |    Online     | Which could deal with streaming input                                                                                                    |
 |       [Paraformer-tiny](https://www.modelscope.cn/models/damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/summary)       |    CN    |  Alibaba Speech Data (200hours)  |    544     |   5.2M    |    Offline     | Lightweight Paraformer model which supports Mandarin command words recognition                                                  |
 |                   [Paraformer-aishell](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-aishell1-pytorch/summary)                   |    CN    |        AISHELL (178hours)        |    4234    |    43M    |    Offline     |                                                                                                                                 |
 |       [ParaformerBert-aishell](https://modelscope.cn/models/damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/summary)       |    CN    |        AISHELL (178hours)        |    4234    |    43M    |    Offline     |                                                                                                                                 |
@@ -25,13 +26,27 @@ Here we provided several pretrained models on different datasets. The details of
 
 #### UniASR Models
 
-|                                                               Model Name                                                               | Language |          Training Data           | Vocab Size | Parameter | Offline/Online | Notes                                                                                                                           |
-|:--------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:--------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
-|       [UniASR](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online/summary)        | CN & EN  | Alibaba Speech Data (60000hours) |    8358    |   100M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
-| [UniASR-large](https://modelscope.cn/models/damo/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline/summary) | CN & EN  | Alibaba Speech Data (60000hours) |    8358    |   220M    |    Offline     | UniASR streaming offline unifying models                                                                                                    |
-|           [UniASR Burmese](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/summary)           | Burmese  |  Alibaba Speech Data (? hours)   |    696     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
-|           [UniASR Hebrew](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/summary)           |  Hebrew  |  Alibaba Speech Data (? hours)   |    1085    |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
-|       [UniASR Urdu](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/summary)                  |   Urdu   |  Alibaba Speech Data (? hours)   |    877     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|                                                                    Model Name                                                                     |    Language     |           Training Data           | Vocab Size | Parameter | Offline/Online | Notes                                                                                                                           |
+|:-------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|:---------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
+|             [UniASR](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online/summary)             |     CN & EN     | Alibaba Speech Data (60000 hours) |    8358    |   100M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|      [UniASR-large](https://modelscope.cn/models/damo/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline/summary)       |     CN & EN     | Alibaba Speech Data (60000 hours) |    8358    |   220M    |    Offline     | UniASR streaming offline unifying models                                                                                                    |
+|          [UniASR English](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-online/summary)           |       EN        | Alibaba Speech Data (10000 hours) |    1080     |    95M    |     Online     | UniASR streaming online unifying models                                                                                                    |
+|          [UniASR Russian](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-online/summary)           |       RU        | Alibaba Speech Data (5000 hours)  |    1664     |    95M    |     Online     | UniASR streaming online unifying models                                                                                                    |
+|           [UniASR Japanese](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-online/summary)           |       JA        | Alibaba Speech Data (5000 hours)  |    5977     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|           [UniASR Korean](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-online/summary)           |       KO        | Alibaba Speech Data (2000 hours)  |    6400     |    95M    |     Online     | UniASR streaming online unifying models                                                                                                    |
+| [UniASR Cantonese (CHS)](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online/summary) | Cantonese (CHS) | Alibaba Speech Data (5000 hours)  |    1468     |    95M    |     Online     | UniASR streaming online unifying models                                                                                                    |
+|         [UniASR Indonesian](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online/summary)         |       ID        | Alibaba Speech Data (1000 hours)  |    1067     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|           [UniASR Vietnamese](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online/summary)           |       VI        | Alibaba Speech Data (1000 hours)  |    1001     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|          [UniASR Spanish](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-online/summary)           |       ES        | Alibaba Speech Data (1000 hours)  |    3445     |    95M    |     Online     | UniASR streaming online unifying models                                                                                                    |
+|         [UniASR Portuguese](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-online/summary)         |       PT        | Alibaba Speech Data (1000 hours)  |    1617     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|           [UniASR French](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-online/summary)           |       FR        | Alibaba Speech Data (1000 hours)  |    3472     |    95M    |     Online     | UniASR streaming online unifying models                                                                                                    |
+|           [UniASR German](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-online/summary)           |       GE        | Alibaba Speech Data (1000 hours)  |    3690     |    95M    |     Online     | UniASR streaming online unifying models                                                                                                    |
+|            [UniASR Persian](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/summary)             |       FA        | Alibaba Speech Data (1000 hours)  |    1257     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|                [UniASR Burmese](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/summary)                 |       MY        | Alibaba Speech Data (1000 hours)  |    696     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|                [UniASR Hebrew](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/summary)                 |       HE        | Alibaba Speech Data (1000 hours)  |    1085    |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+|              [UniASR Urdu](https://modelscope.cn/models/damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/summary)                      |       UR        | Alibaba Speech Data (1000 hours)  |    877     |    95M    |     Online     | UniASR streaming offline unifying models                                                                                                    |
+
+
 
 #### Conformer Models
 
@@ -39,6 +54,7 @@ Here we provided several pretrained models on different datasets. The details of
 |:----------------------------------------------------------------------------------------------------------------------:|:--------:|:---------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
 | [Conformer](https://modelscope.cn/models/damo/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/summary)   |   CN     |  AISHELL (178hours)   |    4234    |    44M    |    Offline     | Duration of input wav <= 20s                                                                                                    |
 | [Conformer](https://www.modelscope.cn/models/damo/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/summary)   |   CN     | AISHELL-2 (1000hours) |    5212    |    44M    |    Offline     | Duration of input wav <= 20s                                                                                                    |
+| [Conformer](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary)   |   EN     | Alibaba Speech Data (10000hours) |    4199    |    220M    |    Offline     | Duration of input wav <= 20s                                                                                                    |
 
 
 #### RNN-T Models
@@ -92,3 +108,19 @@ Here we provided several pretrained models on different datasets. The details of
 |                                                    Model Name                                     |  Language  |    Training Data    | Parameters | Notes |
 |:--------------------------------------------------------------------------------------------------:|:--------------:|:-------------------:|:----------:|:------|
 | [TP-Aligner](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) | CN | Alibaba Speech Data (50000hours) |   37.8M    |    Timestamp prediction, Mandarin, middle size |
+
+### Inverse Text Normalization (ITN) Models
+
+|                                                    Model Name                                                    | Language | Parameters | Notes                    |
+|:----------------------------------------------------------------------------------------------------------------:|:--------:|:----------:|:-------------------------|
+| [English](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-en/summary) |    EN    |   1.54M    | ITN, ASR post-processing |
+| [Russian](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-ru/summary) |    RU    |   17.79M   | ITN, ASR post-processing |
+| [Japanese](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-ja/summary) |    JA    |    6.8M    | ITN, ASR post-processing |
+| [Korean](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-ko/summary) |    KO    |   1.28M    | ITN, ASR post-processing |
+| [Indonesian](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-id/summary) |    ID    |   2.06M    | ITN, ASR post-processing |
+| [Vietnamese](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-vi/summary) |    VI    |   0.92M    | ITN, ASR post-processing |
+| [Tagalog](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-tl/summary) |    TL    |    0.65M     | ITN, ASR post-processing |
+| [Spanish](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-es/summary) |    ES    |   1.32M    | ITN, ASR post-processing |
+| [Portuguese](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-pt/summary) |    PT    |   1.28M    | ITN, ASR post-processing |
+| [French](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-fr/summary) |    FR    |   4.39M    | ITN, ASR post-processing |
+| [German](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-de/summary)|    GE    |   3.95M    | ITN, ASR post-processing |

docs/modelscope_pipeline/itn_pipeline.md

@@ -0,0 +1,63 @@
+# Inverse Text Normalization (ITN)
+
+> **Note**: 
+> The modelscope pipeline supports all the models in [model zoo](https://modelscope.cn/models?page=1&tasks=inverse-text-processing&type=audio) to inference. Here we take the model of the Japanese ITN model as example to demonstrate the usage.
+
+## Inference
+
+### Quick start
+#### [Japanese ITN model](https://modelscope.cn/models/damo/speech_inverse_text_processing_fun-text-processing-itn-ja/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+itn_inference_pipline = pipeline(
+    task=Tasks.inverse_text_processing,
+    model='damo/speech_inverse_text_processing_fun-text-processing-itn-ja',
+    model_revision=None)
+
+itn_result = itn_inference_pipline(text_in='百二十三')
+print(itn_result)
+# 123
+```
+- read text data directly.
+```python
+rec_result = inference_pipeline(text_in='一九九九年に誕生した同商品にちなみ、約三十年前、二十四歳の頃の幸四郎の写真を公開。')
+# 1999年に誕生した同商品にちなみ、約30年前、24歳の頃の幸四郎の写真を公開。
+```
+- text stored via url，example：https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/ja_itn_example.txt
+```python
+rec_result = inference_pipeline(text_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/ja_itn_example.txt')
+```
+
+Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/tree/main/fun_text_processing/inverse_text_normalization)
+
+### API-reference
+#### Define pipeline
+- `task`: `Tasks.inverse_text_processing`
+- `model`: model name in [model zoo](https://modelscope.cn/models?page=1&tasks=inverse-text-processing&type=audio), or model path in local disk
+- `output_dir`: `None` (Default), the output path of results if set
+- `model_revision`: `None` (Default), setting the model version
+
+#### Infer pipeline
+- `text_in`: the input to decode, which could be:
+  - text bytes, `e.g.`: "一九九九年に誕生した同商品にちなみ、約三十年前、二十四歳の頃の幸四郎の写真を公開。"
+  - text file, `e.g.`: https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/ja_itn_example.txt
+  In this case of `text file` input, `output_dir` must be set to save the output results
+
+## Modify Your Own ITN Model
+The rule-based ITN code is open-sourced in [FunTextProcessing](https://github.com/alibaba-damo-academy/FunASR/tree/main/fun_text_processing), users can modify by their own grammar rules for different languages. Let's take Japanese as an example, users can add their own whitelist in ```FunASR/fun_text_processing/inverse_text_normalization/ja/data/whitelist.tsv```. After modified the grammar rules, the users can export and evaluate their own ITN models in local directory.
+
+### Export ITN Model
+Export ITN model via ```FunASR/fun_text_processing/inverse_text_normalization/export_models.py```. An example to export ITN model to local folder is shown as below.
+```shell
+cd FunASR/fun_text_processing/inverse_text_normalization/
+python export_models.py --language ja --export_dir ./itn_models/
+```
+
+### Evaluate ITN Model
+Users can evaluate their own ITN model in local directory via ```FunASR/fun_text_processing/inverse_text_normalization/inverse_normalize.py```. Here is an example:
+```shell
+cd FunASR/fun_text_processing/inverse_text_normalization/
+python inverse_normalize.py --input_file ja_itn_example.txt --cache_dir ./itn_models/ --output_file output.txt --language=ja
+```

docs/modelscope_pipeline/punc_pipeline.md

@@ -1,20 +0,0 @@
-# Punctuation Restoration
-
-## Inference with pipeline
-
-### Quick start
-
-### Inference with you data
-
-### Inference with multi-threads on CPU
-
-### Inference with multi GPU
-
-## Finetune with pipeline
-
-### Quick start
-
-### Finetune with your data
-
-## Inference with your finetuned model
-

docs/modelscope_pipeline/punc_pipeline.md

@@ -0,0 +1 @@
+../../egs_modelscope/punctuation/TEMPLATE/README.md

docs/modelscope_pipeline/quick_start.md

@@ -1,7 +1,7 @@
 # Quick Start
 
 > **Note**: 
-> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take typic model as example to demonstrate the usage.
+> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take typic model as example to demonstrate the usage.
 
 
 ## Inference with pipeline

docs/modelscope_pipeline/sd_pipeline.md

@@ -1,20 +0,0 @@
-# Speaker Diarization
-
-## Inference with pipeline
-
-### Quick start
-
-### Inference with you data
-
-### Inference with multi-threads on CPU
-
-### Inference with multi GPU
-
-## Finetune with pipeline
-
-### Quick start
-
-### Finetune with your data
-
-## Inference with your finetuned model
-

docs/modelscope_pipeline/sd_pipeline.md

@@ -0,0 +1 @@
+../../egs_modelscope/speaker_diarization/TEMPLATE/README.md

docs/modelscope_pipeline/sv_pipeline.md

@@ -1,20 +0,0 @@
-# Speaker Verification
-
-## Inference with pipeline
-
-### Quick start
-
-### Inference with you data
-
-### Inference with multi-threads on CPU
-
-### Inference with multi GPU
-
-## Finetune with pipeline
-
-### Quick start
-
-### Finetune with your data
-
-## Inference with your finetuned model
-

docs/modelscope_pipeline/sv_pipeline.md

@@ -0,0 +1 @@
+../../egs_modelscope/speaker_verification/TEMPLATE/README.md

docs/runtime/websocket_cpp.md

@@ -0,0 +1 @@
+../../funasr/runtime/websocket/readme.md

egs_modelscope/asr/TEMPLATE/README.md

@@ -1,7 +1,7 @@
 # Speech Recognition
 
 > **Note**: 
-> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take the typic models as examples to demonstrate the usage.
+> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take the typic models as examples to demonstrate the usage.
 
 ## Inference
 
@@ -19,22 +19,24 @@ inference_pipeline = pipeline(
 rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
 print(rec_result)
 ```
-#### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
+#### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
 ```python
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
-    model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
+    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
+    model_revision='v1.0.4'
     )
 import soundfile
 speech, sample_rate = soundfile.read("example/asr_example.wav")
 
-param_dict = {"cache": dict(), "is_final": False}
-chunk_stride = 7680# 480ms
-# first chunk, 480ms
+chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
+chunk_stride = chunk_size[1] * 960 # 600ms、480ms
+# first chunk, 600ms
 speech_chunk = speech[0:chunk_stride] 
 rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
 print(rec_result)
-# next chunk, 480ms
+# next chunk, 600ms
 speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
 rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
 print(rec_result)
@@ -42,7 +44,7 @@ print(rec_result)
 Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
 
 #### [UniASR Model](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
-There are three decoding mode for UniASR model(`fast`、`normal`、`offline`), for more model detailes, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
+There are three decoding mode for UniASR model(`fast`、`normal`、`offline`), for more model details, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
 ```python
 decoding_model = "fast" # "fast"、"normal"、"offline"
 inference_pipeline = pipeline(
@@ -59,7 +61,7 @@ Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/
 Undo
 
 #### [MFCCA Model](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
-For more model detailes, please refer to [docs](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
+For more model details, please refer to [docs](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
 ```python
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
@@ -74,15 +76,15 @@ rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyu
 print(rec_result)
 ```
 
-#### API-reference
-##### Define pipeline
+### API-reference
+#### Define pipeline
 - `task`: `Tasks.auto_speech_recognition`
-- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
+- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
 - `ngpu`: `1` (Default), decoding on GPU. If ngpu=0, decoding on CPU
 - `ncpu`: `1` (Default), sets the number of threads used for intraop parallelism on CPU 
 - `output_dir`: `None` (Default), the output path of results if set
 - `batch_size`: `1` (Default), batch size when decoding
-##### Infer pipeline
+#### Infer pipeline
 - `audio_in`: the input to decode, which could be: 
   - wav_path, `e.g.`: asr_example.wav,
   - pcm_path, `e.g.`: asr_example.pcm, 
@@ -100,20 +102,20 @@ print(rec_result)
 ### Inference with multi-thread CPUs or multi GPUs
 FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
 
-- Setting parameters in `infer.sh`
-    - `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
-    - `data_dir`: the dataset dir needs to include `wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
-    - `output_dir`: output dir of the recognition results
-    - `batch_size`: `64` (Default), batch size of inference on gpu
-    - `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
-    - `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
-    - `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
-    - `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
-    - `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
-    - `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast、normal、offline)
-    - `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
-
-- Decode with multi GPUs:
+#### Settings of `infer.sh`
+- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/model_zoo/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
+- `data_dir`: the dataset dir needs to include `wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
+- `output_dir`: output dir of the recognition results
+- `batch_size`: `64` (Default), batch size of inference on gpu
+- `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
+- `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
+- `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
+- `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
+- `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
+- `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast、normal、offline)
+- `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
+
+#### Decode with multi GPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@@ -123,7 +125,7 @@ FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.
     --gpu_inference true \
     --gpuid_list "0,1"
 ```
-- Decode with multi-thread CPUs:
+#### Decode with multi-thread CPUs:
 ```shell
     bash infer.sh \
     --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
@@ -133,7 +135,7 @@ FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.
     --njob 64
 ```
 
-- Results
+#### Results
 
 The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
 

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/README.md

@@ -1,30 +0,0 @@
-# ModelScope Model
-
-## How to finetune and infer using a pretrained Paraformer-large Model
-
-### Finetune
-
-- Modify finetune training related parameters in `finetune.py`
-    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
-    - <strong>batch_bins:</strong> # batch size
-    - <strong>max_epoch:</strong> # number of training epoch
-    - <strong>lr:</strong> # learning rate
-
-- Then you can run the pipeline to finetune with:
-```python
-    python finetune.py
-```
-
-### Inference
-
-Or you can use the finetuned model for inference directly.
-
-- Setting parameters in `infer.py`
-    - <strong>audio_in:</strong> # support wav, url, bytes, and parsed audio format.
-    - <strong>output_dir:</strong> # If the input format is wav.scp, it needs to be set.
-
-- Then you can run the pipeline to infer with:
-```python
-    python infer.py
-```

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/README.md

@@ -0,0 +1 @@
+../../TEMPLATE/README.md

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/demo.py

@@ -0,0 +1,14 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == '__main__':
+    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
+    output_dir = None
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model="damo/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch",
+        output_dir=output_dir,
+    )
+    rec_result = inference_pipeline(audio_in=audio_in)
+    print(rec_result)
+

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/infer.py

@@ -1,14 +0,0 @@
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-if __name__ == '__main__':
-    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
-    output_dir = None
-    inference_pipline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model="damo/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch",
-        output_dir=output_dir,
-    )
-    rec_result = inference_pipline(audio_in=audio_in)
-    print(rec_result)
-

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/infer.py

@@ -0,0 +1 @@
+../../TEMPLATE/infer.py

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/infer.sh

@@ -0,0 +1 @@
+../../TEMPLATE/infer.sh

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/README.md

@@ -0,0 +1 @@
+../../TEMPLATE/README.md

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/demo.py

@@ -0,0 +1,13 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == "__main__":
+    audio_in = "https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav"
+    output_dir = "./results"
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model="damo/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch",
+        output_dir=output_dir,
+    )
+    rec_result = inference_pipeline(audio_in=audio_in)
+    print(rec_result)

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/infer.py

@@ -1,13 +0,0 @@
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-if __name__ == "__main__":
-    audio_in = "https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav"
-    output_dir = "./results"
-    inference_pipline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model="damo/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch",
-        output_dir=output_dir,
-    )
-    rec_result = inference_pipline(audio_in=audio_in)
-    print(rec_result)

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/infer.py

@@ -0,0 +1 @@
+../../TEMPLATE/infer.py

egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/infer.sh

@@ -0,0 +1 @@
+../../TEMPLATE/infer.sh

egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer.py

@@ -16,13 +16,13 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
     else:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k",
         output_dir=output_dir_job,
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
+    inference_pipeline(audio_in=audio_in)
 
 
 def modelscope_infer(params):

egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer.py

@@ -16,13 +16,13 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
     else:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch",
         output_dir=output_dir_job,
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
+    inference_pipeline(audio_in=audio_in)
 
 
 def modelscope_infer(params):

egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/demo.py

@@ -0,0 +1,11 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
+    model_revision='v3.0.0'
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)

egs_modelscope/asr/mfcca/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/infer_after_finetune.py

@@ -1,67 +0,0 @@
-import json
-import os
-import shutil
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-from funasr.utils.compute_wer import compute_wer
-
-
-def modelscope_infer_after_finetune(params):
-    # prepare for decoding
-    pretrained_model_path = os.path.join(os.environ["HOME"], ".cache/modelscope/hub", params["modelscope_model_name"])
-    for file_name in params["required_files"]:
-        if file_name == "configuration.json":
-            with open(os.path.join(pretrained_model_path, file_name)) as f:
-                config_dict = json.load(f)
-                config_dict["model"]["am_model_name"] = params["decoding_model_name"]
-            with open(os.path.join(params["output_dir"], "configuration.json"), "w") as f:
-                json.dump(config_dict, f, indent=4, separators=(',', ': '))
-        else:
-            shutil.copy(os.path.join(pretrained_model_path, file_name),
-                        os.path.join(params["output_dir"], file_name))
-    decoding_path = os.path.join(params["output_dir"], "decode_results")
-    if os.path.exists(decoding_path):
-        shutil.rmtree(decoding_path)
-    os.mkdir(decoding_path)
-
-    # decoding
-    inference_pipeline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model=params["output_dir"],
-        output_dir=decoding_path,
-        batch_size=1
-    )
-    audio_in = os.path.join(params["data_dir"], "wav.scp")
-    inference_pipeline(audio_in=audio_in)
-
-    # computer CER if GT text is set
-    text_in = os.path.join(params["data_dir"], "text")
-    if text_in is not None:
-        text_proc_file = os.path.join(decoding_path, "1best_recog/token")
-        text_proc_file2 = os.path.join(decoding_path, "1best_recog/token_nosep")
-        with open(text_proc_file, 'r') as hyp_reader:
-                with open(text_proc_file2, 'w') as hyp_writer:
-                    for line in hyp_reader:
-                        new_context = line.strip().replace("src","").replace("  "," ").replace("  "," ").strip()
-                        hyp_writer.write(new_context+'\n')
-        text_in2 = os.path.join(decoding_path, "1best_recog/ref_text_nosep")
-        with open(text_in, 'r') as ref_reader:
-            with open(text_in2, 'w') as ref_writer:
-                for line in ref_reader:
-                    new_context = line.strip().replace("src","").replace("  "," ").replace("  "," ").strip()
-                    ref_writer.write(new_context+'\n')
-
-
-        compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.sp.cer"))
-        compute_wer(text_in2, text_proc_file2, os.path.join(decoding_path, "text.nosp.cer"))
-
-if __name__ == '__main__':
-    params = {}
-    params["modelscope_model_name"] = "NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950"
-    params["required_files"] = ["feats_stats.npz", "decoding.yaml", "configuration.json"]
-    params["output_dir"] = "./checkpoint"
-    params["data_dir"] = "./example_data/validation"
-    params["decoding_model_name"] = "valid.acc.ave.pb"
-    modelscope_infer_after_finetune(params)

egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/README.md

@@ -1,19 +0,0 @@
-# ModelScope Model
-
-## How to infer using a pretrained Paraformer-large Model
-
-### Inference
-
-You can use the pretrain model for inference directly.
-
-- Setting parameters in `infer.py`
-    - <strong>audio_in:</strong> # Support wav, url, bytes, and parsed audio format.
-    - <strong>output_dir:</strong> # If the input format is wav.scp, it needs to be set.
-    - <strong>batch_size:</strong> # Set batch size in inference.
-    - <strong>param_dict:</strong> # Set the hotword list in inference.
-
-- Then you can run the pipeline to infer with:
-```python
-    python infer.py
-```
-

egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/README.md

@@ -0,0 +1 @@
+../../TEMPLATE/README.md

egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/finetune.py

@@ -0,0 +1,37 @@
+import os
+
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+
+from funasr.datasets.ms_dataset import MsDataset
+from funasr.utils.modelscope_param import modelscope_args
+
+
+def modelscope_finetune(params):
+    if not os.path.exists(params.output_dir):
+        os.makedirs(params.output_dir, exist_ok=True)
+    # dataset split ["train", "validation"]
+    ds_dict = MsDataset.load(params.data_path)
+    kwargs = dict(
+        model=params.model,
+        model_revision="v1.0.2",
+        data_dir=ds_dict,
+        dataset_type=params.dataset_type,
+        work_dir=params.output_dir,
+        batch_bins=params.batch_bins,
+        max_epoch=params.max_epoch,
+        lr=params.lr)
+    trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
+    trainer.train()
+
+
+if __name__ == '__main__':
+    params = modelscope_args(model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404", data_path="./data")
+    params.output_dir = "./checkpoint"              # 模型保存路径
+    params.data_path = "./example_data/"            # 数据路径
+    params.dataset_type = "large"                   # finetune contextual paraformer模型只能使用large dataset
+    params.batch_bins = 200000                      # batch size，如果dataset_type="small"，batch_bins单位为fbank特征帧数，如果dataset_type="large"，batch_bins单位为毫秒，
+    params.max_epoch = 20                           # 最大训练轮数
+    params.lr = 0.0002                              # 设置学习率
+
+    modelscope_finetune(params)

egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.sh

@@ -12,7 +12,7 @@ output_dir="./results"
 batch_size=64
 gpu_inference=true    # whether to perform gpu decoding
 gpuid_list="0,1"    # set gpus, e.g., gpuid_list="0,1"
-njob=64    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+njob=10    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
 checkpoint_dir=
 checkpoint_name="valid.cer_ctc.ave.pb"
 hotword_txt=None
@@ -55,8 +55,8 @@ if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
             --audio_in ${output_dir}/split/wav.$JOB.scp \
             --output_dir ${output_dir}/output.$JOB \
             --batch_size ${batch_size} \
-            --gpuid ${gpuid} \
-            --hotword_txt ${hotword_txt}
+            --hotword_txt ${hotword_txt} \
+            --gpuid ${gpuid}
         }&
     done
     wait

egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer_aishell1_subtest_demo.py

@@ -19,11 +19,15 @@ if __name__ == '__main__':
         os.makedirs(work_dir)
     wav_file_path = os.path.join(work_dir, "wav.scp")
     
+    counter = 0
     with codecs.open(wav_file_path, 'w') as fin: 
         for line in ds_dict:
+            counter += 1
             wav = line["Audio:FILE"]
             idx = wav.split("/")[-1].split(".")[0]
             fin.writelines(idx + " " + wav + "\n")
+            if counter == 50:
+                break
     audio_in = wav_file_path         
 
     inference_pipeline = pipeline(

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/infer.py

@@ -0,0 +1,39 @@
+import os
+import logging
+import torch
+import soundfile
+
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+from modelscope.utils.logger import get_logger
+
+logger = get_logger(log_level=logging.CRITICAL)
+logger.setLevel(logging.CRITICAL)
+
+os.environ["MODELSCOPE_CACHE"] = "./"
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
+    model_revision='v1.0.4'
+)
+
+model_dir = os.path.join(os.environ["MODELSCOPE_CACHE"], "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online")
+speech, sample_rate = soundfile.read(os.path.join(model_dir, "example/asr_example.wav"))
+speech_length = speech.shape[0]
+
+sample_offset = 0
+chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
+stride_size =  chunk_size[1] * 960
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
+final_result = ""
+
+for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
+    if sample_offset + stride_size >= speech_length - 1:
+        stride_size = speech_length - sample_offset
+        param_dict["is_final"] = True
+    rec_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + stride_size],
+                                    param_dict=param_dict)
+    if len(rec_result) != 0:
+        final_result += rec_result['text'] + " "
+        print(rec_result)
+print(final_result)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md

@@ -1,76 +0,0 @@
-# ModelScope Model
-
-## How to finetune and infer using a pretrained Paraformer-large Model
-
-### Finetune
-
-- Modify finetune training related parameters in `finetune.py`
-    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include files: `train/wav.scp`, `train/text`; `validation/wav.scp`, `validation/text`
-    - <strong>dataset_type:</strong> # for dataset larger than 1000 hours, set as `large`, otherwise set as `small`
-    - <strong>batch_bins:</strong> # batch size. For dataset_type is `small`, `batch_bins` indicates the feature frames. For dataset_type is `large`, `batch_bins` indicates the duration in ms
-    - <strong>max_epoch:</strong> # number of training epoch
-    - <strong>lr:</strong> # learning rate
-
-- Then you can run the pipeline to finetune with:
-```python
-    python finetune.py
-```
-
-### Inference
-
-Or you can use the finetuned model for inference directly.
-
-- Setting parameters in `infer.sh`
-    - <strong>model:</strong> # model name on ModelScope
-    - <strong>data_dir:</strong> # the dataset dir needs to include `${data_dir}/wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
-    - <strong>output_dir:</strong> # result dir
-    - <strong>batch_size:</strong> # batchsize of inference
-    - <strong>gpu_inference:</strong> # whether to perform gpu decoding, set false for cpu decoding
-    - <strong>gpuid_list:</strong> # set gpus, e.g., gpuid_list="0,1"
-    - <strong>njob:</strong> # the number of jobs for CPU decoding, if `gpu_inference`=false, use CPU decoding, please set `njob`
-
-- Decode with multi GPUs:
-```shell
-    bash infer.sh \
-    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
-    --data_dir "./data/test" \
-    --output_dir "./results" \
-    --batch_size 64 \
-    --gpu_inference true \
-    --gpuid_list "0,1"
-```
-
-- Decode with multi-thread CPUs:
-```shell
-    bash infer.sh \
-    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
-    --data_dir "./data/test" \
-    --output_dir "./results" \
-    --gpu_inference false \
-    --njob 64
-```
-
-- Results
-
-The decoding results can be found in `${output_dir}/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
-
-If you decode the SpeechIO test sets, you can use textnorm with `stage`=3, and `DETAILS.txt`, `RESULTS.txt` record the results and CER after text normalization.
-
-### Inference using local finetuned model
-
-- Modify inference related parameters in `infer_after_finetune.py`
-    - <strong>modelscope_model_name: </strong> # model name on ModelScope
-    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
-    - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
-    - <strong>batch_size:</strong> # batchsize of inference  
-
-- Then you can run the pipeline to finetune with:
-```python
-    python infer_after_finetune.py
-```
-
-- Results
-
-The decoding results can be found in `$output_dir/decoding_results/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md

@@ -0,0 +1 @@
+../TEMPLATE/README.md

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh

@@ -1,103 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-set -u
-set -o pipefail
-
-stage=1
-stop_stage=2
-model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-data_dir="./data/test"
-output_dir="./results"
-batch_size=64
-gpu_inference=true    # whether to perform gpu decoding
-gpuid_list="0,1"    # set gpus, e.g., gpuid_list="0,1"
-njob=64    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
-checkpoint_dir=
-checkpoint_name="valid.cer_ctc.ave.pb"
-
-. utils/parse_options.sh || exit 1;
-
-if ${gpu_inference} == "true"; then
-    nj=$(echo $gpuid_list | awk -F "," '{print NF}')
-else
-    nj=$njob
-    batch_size=1
-    gpuid_list=""
-    for JOB in $(seq ${nj}); do
-        gpuid_list=$gpuid_list"-1,"
-    done
-fi
-
-mkdir -p $output_dir/split
-split_scps=""
-for JOB in $(seq ${nj}); do
-    split_scps="$split_scps $output_dir/split/wav.$JOB.scp"
-done
-perl utils/split_scp.pl ${data_dir}/wav.scp ${split_scps}
-
-if [ -n "${checkpoint_dir}" ]; then
-  python utils/prepare_checkpoint.py ${model} ${checkpoint_dir} ${checkpoint_name}
-  model=${checkpoint_dir}/${model}
-fi
-
-if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
-    echo "Decoding ..."
-    gpuid_list_array=(${gpuid_list//,/ })
-    for JOB in $(seq ${nj}); do
-        {
-        id=$((JOB-1))
-        gpuid=${gpuid_list_array[$id]}
-        mkdir -p ${output_dir}/output.$JOB
-        python infer.py \
-            --model ${model} \
-            --audio_in ${output_dir}/split/wav.$JOB.scp \
-            --output_dir ${output_dir}/output.$JOB \
-            --batch_size ${batch_size} \
-            --gpuid ${gpuid}
-        }&
-    done
-    wait
-
-    mkdir -p ${output_dir}/1best_recog
-    for f in token score text; do
-        if [ -f "${output_dir}/output.1/1best_recog/${f}" ]; then
-          for i in $(seq "${nj}"); do
-              cat "${output_dir}/output.${i}/1best_recog/${f}"
-          done | sort -k1 >"${output_dir}/1best_recog/${f}"
-        fi
-    done
-fi
-
-if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
-    echo "Computing WER ..."
-    cp ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
-    cp ${data_dir}/text ${output_dir}/1best_recog/text.ref
-    python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
-    tail -n 3 ${output_dir}/1best_recog/text.cer
-fi
-
-if [ $stage -le 3 ] && [ $stop_stage -ge 3 ];then
-    echo "SpeechIO TIOBE textnorm"
-    echo "$0 --> Normalizing REF text ..."
-    ./utils/textnorm_zh.py \
-        --has_key --to_upper \
-        ${data_dir}/text \
-        ${output_dir}/1best_recog/ref.txt
-
-    echo "$0 --> Normalizing HYP text ..."
-    ./utils/textnorm_zh.py \
-        --has_key --to_upper \
-        ${output_dir}/1best_recog/text.proc \
-        ${output_dir}/1best_recog/rec.txt
-    grep -v $'\t$' ${output_dir}/1best_recog/rec.txt > ${output_dir}/1best_recog/rec_non_empty.txt
-
-    echo "$0 --> computing WER/CER and alignment ..."
-    ./utils/error_rate_zh \
-        --tokenizer char \
-        --ref ${output_dir}/1best_recog/ref.txt \
-        --hyp ${output_dir}/1best_recog/rec_non_empty.txt \
-        ${output_dir}/1best_recog/DETAILS.txt | tee ${output_dir}/1best_recog/RESULTS.txt
-    rm -rf ${output_dir}/1best_recog/rec.txt ${output_dir}/1best_recog/rec_non_empty.txt
-fi
-

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh

@@ -0,0 +1 @@
+../TEMPLATE/infer.sh

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py

@@ -1,48 +0,0 @@
-import json
-import os
-import shutil
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-from modelscope.hub.snapshot_download import snapshot_download
-
-from funasr.utils.compute_wer import compute_wer
-
-def modelscope_infer_after_finetune(params):
-    # prepare for decoding
-
-    try:
-        pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
-    except BaseException:
-        raise BaseException(f"Please download pretrain model from ModelScope firstly.")
-    shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
-    decoding_path = os.path.join(params["output_dir"], "decode_results")
-    if os.path.exists(decoding_path):
-        shutil.rmtree(decoding_path)
-    os.mkdir(decoding_path)
-
-    # decoding
-    inference_pipeline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model=pretrained_model_path,
-        output_dir=decoding_path,
-        batch_size=params["batch_size"]
-    )
-    audio_in = os.path.join(params["data_dir"], "wav.scp")
-    inference_pipeline(audio_in=audio_in)
-
-    # computer CER if GT text is set
-    text_in = os.path.join(params["data_dir"], "text")
-    if os.path.exists(text_in):
-        text_proc_file = os.path.join(decoding_path, "1best_recog/text")
-        compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
-
-
-if __name__ == '__main__':
-    params = {}
-    params["modelscope_model_name"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-    params["output_dir"] = "./checkpoint"
-    params["data_dir"] = "./data/test"
-    params["decoding_model_name"] = "valid.acc.ave_10best.pb"
-    params["batch_size"] = 64
-    modelscope_infer_after_finetune(params)

egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/infer.py

@@ -16,14 +16,14 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
     else:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch",
         output_dir=output_dir_job,
         batch_size=64
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
+    inference_pipeline(audio_in=audio_in)
 
 
 def modelscope_infer(params):

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/README.md

@@ -1,30 +0,0 @@
-# ModelScope Model
-
-## How to finetune and infer using a pretrained Paraformer-large Model
-
-### Finetune
-
-- Modify finetune training related parameters in `finetune.py`
-    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
-    - <strong>batch_bins:</strong> # batch size
-    - <strong>max_epoch:</strong> # number of training epoch
-    - <strong>lr:</strong> # learning rate
-
-- Then you can run the pipeline to finetune with:
-```python
-    python finetune.py
-```
-
-### Inference
-
-Or you can use the finetuned model for inference directly.
-
-- Setting parameters in `infer.py`
-    - <strong>audio_in:</strong> # support wav, url, bytes, and parsed audio format.
-    - <strong>output_dir:</strong> # If the input format is wav.scp, it needs to be set.
-
-- Then you can run the pipeline to infer with:
-```python
-    python infer.py
-```

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/README.md

@@ -0,0 +1 @@
+../TEMPLATE/README.md

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/demo.py

@@ -0,0 +1,15 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == '__main__':
+    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
+    output_dir = None
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model="damo/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch",
+        output_dir=output_dir,
+        batch_size=1,
+    )
+    rec_result = inference_pipeline(audio_in=audio_in)
+    print(rec_result)
+

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/infer.py

@@ -1,15 +0,0 @@
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-if __name__ == '__main__':
-    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
-    output_dir = None
-    inference_pipline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model="damo/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch",
-        output_dir=output_dir,
-        batch_size=32,
-    )
-    rec_result = inference_pipline(audio_in=audio_in)
-    print(rec_result)
-

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/infer.py

@@ -0,0 +1 @@
+../TEMPLATE/infer.py

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/infer.sh

@@ -0,0 +1 @@
+../TEMPLATE/infer.sh

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/README.md

@@ -0,0 +1 @@
+../TEMPLATE/README.md

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/demo.py

@@ -0,0 +1,13 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == "__main__":
+    audio_in = "https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav"
+    output_dir = "./results"
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model="damo/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch",
+        output_dir=output_dir,
+    )
+    rec_result = inference_pipeline(audio_in=audio_in)
+    print(rec_result)

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/infer.py

@@ -1,13 +0,0 @@
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-if __name__ == "__main__":
-    audio_in = "https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav"
-    output_dir = "./results"
-    inference_pipline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model="damo/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch",
-        output_dir=output_dir,
-    )
-    rec_result = inference_pipline(audio_in=audio_in)
-    print(rec_result)

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/infer.py

@@ -0,0 +1 @@
+../TEMPLATE/infer.py

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/infer.sh

@@ -0,0 +1 @@
+../TEMPLATE/infer.sh

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/infer.py

@@ -14,24 +14,26 @@ os.environ["MODELSCOPE_CACHE"] = "./"
 inference_pipeline = pipeline(
     task=Tasks.auto_speech_recognition,
     model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
-    model_revision='v1.0.2')
+    model_revision='v1.0.4'
+)
 
 model_dir = os.path.join(os.environ["MODELSCOPE_CACHE"], "damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online")
 speech, sample_rate = soundfile.read(os.path.join(model_dir, "example/asr_example.wav"))
 speech_length = speech.shape[0]
 
 sample_offset = 0
-step = 4800  #300ms
-param_dict = {"cache": dict(), "is_final": False}
+chunk_size = [8, 8, 4] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
+stride_size =  chunk_size[1] * 960
+param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
 final_result = ""
 
-for sample_offset in range(0, speech_length, min(step, speech_length - sample_offset)):
-    if sample_offset + step >= speech_length - 1:
-        step = speech_length - sample_offset
+for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
+    if sample_offset + stride_size >= speech_length - 1:
+        stride_size = speech_length - sample_offset
         param_dict["is_final"] = True
-    rec_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + step],
+    rec_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + stride_size],
                                     param_dict=param_dict)
-    if len(rec_result) != 0 and rec_result['text'] != "sil" and rec_result['text'] != "waiting_for_more_voice":
-        final_result += rec_result['text']
-    print(rec_result)
-print(final_result)
+    if len(rec_result) != 0:
+        final_result += rec_result['text'] + " "
+        print(rec_result)
+print(final_result.strip())

egs_modelscope/asr/paraformerbert/speech_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/infer.py

@@ -4,11 +4,11 @@ from modelscope.utils.constant import Tasks
 if __name__ == '__main__':
     audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
     output_dir = None
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in)
+    rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)
 

egs_modelscope/asr/paraformerbert/speech_paraformerbert_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in)
+    rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cantonese-CHS.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cantonese-CHS.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-cn-dialect-16k-vocab8358-tensorflow1-offline/infer.py

@@ -4,11 +4,11 @@ from modelscope.utils.constant import Tasks
 if __name__ == '__main__':
     audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
     output_dir = None
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-cn-dialect-16k-vocab8358-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in)
+    rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)
 

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-cn-dialect-16k-vocab8358-tensorflow1-online/infer.py

@@ -4,11 +4,11 @@ from modelscope.utils.constant import Tasks
 if __name__ == '__main__':
     audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
     output_dir = None
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-cn-dialect-16k-vocab8358-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in)
+    rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)
 

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_de.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_de.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_es.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_es.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/infer.py

@@ -16,14 +16,14 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
     else:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline",
         output_dir=output_dir_job,
         batch_size=1
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
 
 
 def modelscope_infer(params):

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/infer.py

@@ -16,14 +16,14 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
     else:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online",
         output_dir=output_dir_job,
         batch_size=1
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
 
 
 def modelscope_infer(params):

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_fr.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_fr.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_he.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_id.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_id.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ja.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ja.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ko.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ko.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_my.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_pt.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_pt.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ru.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ru.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ur.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-offline/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_vi.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online/infer.py

@@ -4,10 +4,10 @@ from modelscope.utils.constant import Tasks
 if __name__ == "__main__":
     audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_vi.wav"
     output_dir = "./results"
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
     print(rec_result)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline/infer.py

@@ -4,11 +4,11 @@ from modelscope.utils.constant import Tasks
 if __name__ == '__main__':
     audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
     output_dir = None
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in)
+    rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)
 

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online/infer.py

@@ -4,11 +4,11 @@ from modelscope.utils.constant import Tasks
 if __name__ == '__main__':
     audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
     output_dir = None
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in)
+    rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)
 

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py

@@ -16,14 +16,14 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
     else:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline",
         output_dir=output_dir_job,
         batch_size=1
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
+    inference_pipeline(audio_in=audio_in)
 
 def modelscope_infer(params):
     # prepare for multi-GPU decoding

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py

@@ -16,14 +16,14 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
     else:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online",
         output_dir=output_dir_job,
         batch_size=1
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
+    inference_pipeline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
 
 
 def modelscope_infer(params):

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-offline/infer.py

@@ -4,11 +4,11 @@ from modelscope.utils.constant import Tasks
 if __name__ == '__main__':
     audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
     output_dir = None
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-offline",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in)
+    rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)
 

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-online/infer.py

@@ -4,11 +4,11 @@ from modelscope.utils.constant import Tasks
 if __name__ == '__main__':
     audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
     output_dir = None
-    inference_pipline = pipeline(
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
         model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-online",
         output_dir=output_dir,
     )
-    rec_result = inference_pipline(audio_in=audio_in)
+    rec_result = inference_pipeline(audio_in=audio_in)
     print(rec_result)
 

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md

@@ -1,46 +1,246 @@
-# ModelScope Model
+# Speech Recognition
 
-## How to finetune and infer using a pretrained Paraformer-large Model
+> **Note**: 
+> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetine. Here we take the typic models as examples to demonstrate the usage.
 
-### Finetune
+## Inference
 
-- Modify finetune training related parameters in `finetune.py`
-    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
-    - <strong>batch_bins:</strong> # batch size
-    - <strong>max_epoch:</strong> # number of training epoch
-    - <strong>lr:</strong> # learning rate
+### Quick start
+#### [Paraformer Model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
 
-- Then you can run the pipeline to finetune with:
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)
+```
+#### [Paraformer-online Model](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary)
+```python
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online',
+    )
+import soundfile
+speech, sample_rate = soundfile.read("example/asr_example.wav")
+
+param_dict = {"cache": dict(), "is_final": False}
+chunk_stride = 7680# 480ms
+# first chunk, 480ms
+speech_chunk = speech[0:chunk_stride] 
+rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
+print(rec_result)
+# next chunk, 480ms
+speech_chunk = speech[chunk_stride:chunk_stride+chunk_stride]
+rec_result = inference_pipeline(audio_in=speech_chunk, param_dict=param_dict)
+print(rec_result)
+```
+Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241)
+
+#### [UniASR Model](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
+There are three decoding mode for UniASR model(`fast`、`normal`、`offline`), for more model detailes, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary)
+```python
+decoding_model = "fast" # "fast"、"normal"、"offline"
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825',
+    param_dict={"decoding_model": decoding_model})
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)
+```
+The decoding mode of `fast` and `normal` is fake streaming, which could be used for evaluating of recognition accuracy.
+Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
+#### [RNN-T-online model]()
+Undo
+
+#### [MFCCA Model](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
+For more model detailes, please refer to [docs](https://www.modelscope.cn/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/summary)
 ```python
-    python finetune.py
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
+    model_revision='v3.0.0'
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)
+```
+
+#### API-reference
+##### Define pipeline
+- `task`: `Tasks.auto_speech_recognition`
+- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
+- `ngpu`: `1` (Default), decoding on GPU. If ngpu=0, decoding on CPU
+- `ncpu`: `1` (Default), sets the number of threads used for intraop parallelism on CPU 
+- `output_dir`: `None` (Default), the output path of results if set
+- `batch_size`: `1` (Default), batch size when decoding
+##### Infer pipeline
+- `audio_in`: the input to decode, which could be: 
+  - wav_path, `e.g.`: asr_example.wav,
+  - pcm_path, `e.g.`: asr_example.pcm, 
+  - audio bytes stream, `e.g.`: bytes data from a microphone
+  - audio sample point，`e.g.`: `audio, rate = soundfile.read("asr_example_zh.wav")`, the dtype is numpy.ndarray or torch.Tensor
+  - wav.scp, kaldi style wav list (`wav_id \t wav_path`), `e.g.`: 
+  ```text
+  asr_example1  ./audios/asr_example1.wav
+  asr_example2  ./audios/asr_example2.wav
+  ```
+  In this case of `wav.scp` input, `output_dir` must be set to save the output results
+- `audio_fs`: audio sampling rate, only set when audio_in is pcm audio
+- `output_dir`: None (Default), the output path of results if set
+
+### Inference with multi-thread CPUs or multi GPUs
+FunASR also offer recipes [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
+
+- Setting parameters in `infer.sh`
+    - `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
+    - `data_dir`: the dataset dir needs to include `wav.scp`. If `${data_dir}/text` is also exists, CER will be computed
+    - `output_dir`: output dir of the recognition results
+    - `batch_size`: `64` (Default), batch size of inference on gpu
+    - `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
+    - `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
+    - `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
+    - `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
+    - `checkpoint_name`: only used for infer finetuned models, `valid.cer_ctc.ave.pb` (Default), which checkpoint is used to infer
+    - `decoding_mode`: `normal` (Default), decoding mode for UniASR model(fast、normal、offline)
+    - `hotword_txt`: `None` (Default), hotword file for contextual paraformer model(the hotword file name ends with .txt")
+
+- Decode with multi GPUs:
+```shell
+    bash infer.sh \
+    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+    --data_dir "./data/test" \
+    --output_dir "./results" \
+    --batch_size 64 \
+    --gpu_inference true \
+    --gpuid_list "0,1"
+```
+- Decode with multi-thread CPUs:
+```shell
+    bash infer.sh \
+    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+    --data_dir "./data/test" \
+    --output_dir "./results" \
+    --gpu_inference false \
+    --njob 64
 ```
 
-### Inference
+- Results
+
+The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
+
+If you decode the SpeechIO test sets, you can use textnorm with `stage`=3, and `DETAILS.txt`, `RESULTS.txt` record the results and CER after text normalization.
 
-Or you can use the finetuned model for inference directly.
 
-- Setting parameters in `infer.py`
-    - <strong>audio_in:</strong> # support wav, url, bytes, and parsed audio format.
-    - <strong>output_dir:</strong> # If the input format is wav.scp, it needs to be set.
+## Finetune with pipeline
 
-- Then you can run the pipeline to infer with:
+### Quick start
+[finetune.py](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/finetune.py)
 ```python
-    python infer.py
+import os
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+from modelscope.msdatasets.audio.asr_dataset import ASRDataset
+
+def modelscope_finetune(params):
+    if not os.path.exists(params.output_dir):
+        os.makedirs(params.output_dir, exist_ok=True)
+    # dataset split ["train", "validation"]
+    ds_dict = ASRDataset.load(params.data_path, namespace='speech_asr')
+    kwargs = dict(
+        model=params.model,
+        data_dir=ds_dict,
+        dataset_type=params.dataset_type,
+        work_dir=params.output_dir,
+        batch_bins=params.batch_bins,
+        max_epoch=params.max_epoch,
+        lr=params.lr)
+    trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
+    trainer.train()
+
+
+if __name__ == '__main__':
+    from funasr.utils.modelscope_param import modelscope_args
+    params = modelscope_args(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+    params.output_dir = "./checkpoint"                      # 模型保存路径
+    params.data_path = "speech_asr_aishell1_trainsets"      # 数据路径，可以为modelscope中已上传数据，也可以是本地数据
+    params.dataset_type = "small"                           # 小数据量设置small，若数据量大于1000小时，请使用large
+    params.batch_bins = 2000                                # batch size，如果dataset_type="small"，batch_bins单位为fbank特征帧数，如果dataset_type="large"，batch_bins单位为毫秒，
+    params.max_epoch = 50                                   # 最大训练轮数
+    params.lr = 0.00005                                     # 设置学习率
+    
+    modelscope_finetune(params)
+```
+
+```shell
+python finetune.py &> log.txt &
 ```
 
-### Inference using local finetuned model
+### Finetune with your data
+
+- Modify finetune training related parameters in [finetune.py](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/finetune.py)
+    - `output_dir`: result dir
+    - `data_dir`: the dataset dir needs to include files: `train/wav.scp`, `train/text`; `validation/wav.scp`, `validation/text`
+    - `dataset_type`: for dataset larger than 1000 hours, set as `large`, otherwise set as `small`
+    - `batch_bins`: batch size. For dataset_type is `small`, `batch_bins` indicates the feature frames. For dataset_type is `large`, `batch_bins` indicates the duration in ms
+    - `max_epoch`: number of training epoch
+    - `lr`: learning rate
 
-- Modify inference related parameters in `infer_after_finetune.py`
-    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
-    - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
+- Training data formats：
+```sh
+cat ./example_data/text
+BAC009S0002W0122 而 对 楼 市 成 交 抑 制 作 用 最 大 的 限 购
+BAC009S0002W0123 也 成 为 地 方 政 府 的 眼 中 钉
+english_example_1 hello world
+english_example_2 go swim 去 游 泳
+
+cat ./example_data/wav.scp
+BAC009S0002W0122 /mnt/data/wav/train/S0002/BAC009S0002W0122.wav
+BAC009S0002W0123 /mnt/data/wav/train/S0002/BAC009S0002W0123.wav
+english_example_1 /mnt/data/wav/train/S0002/english_example_1.wav
+english_example_2 /mnt/data/wav/train/S0002/english_example_2.wav
+```
 
 - Then you can run the pipeline to finetune with:
-```python
-    python infer_after_finetune.py
+```shell
+python finetune.py
 ```
+If you want finetune with multi-GPUs, you could:
+```shell
+CUDA_VISIBLE_DEVICES=1,2 python -m torch.distributed.launch --nproc_per_node 2 finetune.py > log.txt 2>&1
+```
+## Inference with your finetuned model
 
-- Results
+- Setting parameters in [egs_modelscope/asr/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) is the same with [docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/egs_modelscope/asr/TEMPLATE#inference-with-multi-thread-cpus-or-multi-gpus), `model` is the model name from modelscope, which you finetuned.
 
-The decoding results can be found in `$output_dir/decoding_results/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
+- Decode with multi GPUs:
+```shell
+    bash infer.sh \
+    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+    --data_dir "./data/test" \
+    --output_dir "./results" \
+    --batch_size 64 \
+    --gpu_inference true \
+    --gpuid_list "0,1" \
+    --checkpoint_dir "./checkpoint" \
+    --checkpoint_name "valid.cer_ctc.ave.pb"
+```
+- Decode with multi-thread CPUs:
+```shell
+    bash infer.sh \
+    --model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+    --data_dir "./data/test" \
+    --output_dir "./results" \
+    --gpu_inference false \
+    --njob 64 \
+    --checkpoint_dir "./checkpoint" \
+    --checkpoint_name "valid.cer_ctc.ave.pb"
+```

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/demo.py

@@ -0,0 +1,16 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == '__main__':
+    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
+    output_dir = None
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model='damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+        vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+        punc_model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
+        output_dir=output_dir
+    )
+    rec_result = inference_pipeline(audio_in=audio_in)
+    print(rec_result)
+