Нема описа

yhliang 742d96d8e4 update read.md		пре 2 година
.github	742d96d8e4 update read.md	пре 2 година
docs	77a7b40a7c readme	пре 3 година
docs_cn	2f7e99e1dd update docs	пре 3 година
docs_m2met2	e09d17de60 add m2met2 docs cn version	пре 2 година
docs_m2met2_cn	e09d17de60 add m2met2 docs cn version	пре 2 година
egs	cf843d144a fix compute cer problems	пре 3 година
egs_modelscope	0efa2aa971 update uniasr infer recipe	пре 2 година
fun_text_processing	12a7adfdf3 update version 0.1.6	пре 3 година
funasr	60d38fa9ca onnx libtorch python runtime optim	пре 2 година
tests	2aee9dc465 update	пре 3 година
.gitignore	508e518b12 update cif onnx	пре 3 година
LICENSE	c087854f71 create	пре 3 година
README.md	742d96d8e4 update read.md	пре 2 година
setup.py	317dac5b75 readme	пре 3 година

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

FunASR hopes to build a bridge between academic research and industrial applications on speech recognition. By supporting the training & finetuning of the industrial-grade speech recognition model released on ModelScope, researchers and developers can conduct research and production of speech recognition models more conveniently, and promote the development of speech recognition ecology. ASR for Fun！

M2MET2.0 Guidence_CN | M2MET2.0 Guidence_EN

Multi-Channel Multi-Party Meeting Transcription 2.0 (M2MET2.0) Challenge

We are pleased to announce that the M2MeT2.0 challenge will be held in the near future. The baseline system is conducted on FunASR and provided as a receipe of AliMeeting corpus. For more details you can see the guidence of M2MET2.0 (CN/EN).

What's new:

For the release notes, please ref to news

Highlights

Many types of typical models are supported, e.g., Tranformer, Conformer, Paraformer.
We have released large number of academic and industrial pretrained models on ModelScope
The pretrained model Paraformer-large obtains the best performance on many tasks in SpeechIO leaderboard
FunASR supplies a easy-to-use pipeline to finetune pretrained models from ModelScope
Compared to Espnet framework, the training speed of large-scale datasets in FunASR is much faster owning to the optimized dataloader.

Installation

pip install "modelscope[audio_asr]" --upgrade -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
git clone https://github.com/alibaba/FunASR.git && cd FunASR
pip install -e ./

For more details, please ref to installation

Usage

For users who are new to FunASR and ModelScope, please refer to FunASR Docs(CN / EN)

Contact

If you have any questions about FunASR, please contact us by

email: funasr@list.alibaba-inc.com

Dingding group	Wechat group

Contributors

Acknowledge

We borrowed a lot of code from Kaldi for data preparation.
We borrowed a lot of code from ESPnet. FunASR follows up the training and finetuning pipelines of ESPnet.
We referred Wenet for building dataloader for large scale data training.
We acknowledge DeepScience for contributing the grpc service.

License

This project is licensed under the The MIT License. FunASR also contains various third-party components and some code modified from other repos under other open source licenses.

Citations

@inproceedings{gao2020universal,
  title={Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model},
  author={Gao, Zhifu and Zhang, Shiliang and Lei, Ming and McLoughlin, Ian},
  booktitle={arXiv preprint arXiv:2010.14099},
  year={2020}
}

@inproceedings{gao2022paraformer,
  title={Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition},
  author={Gao, Zhifu and Zhang, Shiliang and McLoughlin, Ian and Yan, Zhijie},
  booktitle={INTERSPEECH},
  year={2022}
}
@inproceedings{Shi2023AchievingTP,
  title={Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Model},
  author={Xian Shi and Yanni Chen and Shiliang Zhang and Zhijie Yan},
  booktitle={arXiv preprint arXiv:2301.12343}
  year={2023}
}

README.md