Почетна Преглед Помоћ
Регистрација Пријавите се
siweilian
/
FunASR
3
0
Креирај огранак 0
Датотеке Дискусије 0 Захтеви за спајање 0 Вики
Грана: dev_bj_2pass_grpc
Гране Ознаке
FunASR
/
funasr
/
runtime
boji123 e1a759a356 [refator] modify grpc cmake пре 2 година
..
csharp c2a2575f19 add c# assembly for fsmn vad (#650) пре 2 година
deploy_tools 3e0230bcb0 [funasr-runtime-deploy 0.0.6] add SSL on-off and rationalize remove/start (#713) пре 2 година
docs 1076591b29 docs zh пре 2 година
grpc e1a759a356 [refator] modify grpc cmake пре 2 година
html5 77dc80f036 add is_final for html5 and java client (#795) пре 2 година
java 77dc80f036 add is_final for html5 and java client (#795) пре 2 година
onnxruntime b07213188f update пре 2 година
python df6772e5b6 [refator] optimize grpc client pipeline and instruction пре 2 година
ssl_key 546e6a658a update server.key пре 2 година
triton_gpu 98abc0e5ac update setup (#686) пре 2 година
websocket e9862461bc add cpp websocket online 2pass srv пре 2 година
__init__.py 865ae89f0a export model пре 3 година
readme.md bc1e5c6f93 docs пре 2 година
readme_cn.md b395682268 Update readme_cn.md пре 2 година
run_server.sh 6b840d5143 Merge remote-tracking branch 'origin/main' пре 2 година

readme.md

FunASR runtime-SDK

中文文档（点击此处）

FunASR is a speech recognition framework developed by the Speech Lab of DAMO Academy, which integrates industrial-level models in the fields of speech endpoint detection, speech recognition, punctuation segmentation, and more. It has attracted many developers to participate in experiencing and developing. To solve the last mile of industrial landing and integrate models into business, we have developed the FunASR runtime-SDK. The SDK supports several service deployments, including:

  • File transcription service, Mandarin, CPU version, done
  • File transcription service, Mandarin, GPU version, in progress
  • File transcription service, English, in progress
  • Streaming speech recognition service, is in progress
  • and more.

File Transcription Service, Mandarin (CPU)

Currently, the FunASR runtime-SDK-0.0.1 version supports the deployment of file transcription service, Mandarin (CPU version), with a complete speech recognition chain that can transcribe tens of hours of audio into punctuated text, and supports recognition for more than a hundred concurrent streams.

To meet the needs of different users, we have prepared different tutorials with text and images for both novice and advanced developers.

Technical Principles

The technical principles and documentation behind FunASR explain the underlying technology, recognition accuracy, computational efficiency, and core advantages of the framework, including convenience, high precision, high efficiency, and support for long audio chains. For detailed information, please refer to the documentation available by docs.

Deployment Tutorial

The documentation mainly targets novice users who have no need for modifications or customization. It supports downloading model deployments from modelscope and also supports deploying models that users have fine-tuned. For detailed tutorials, please refer to docs.

Advanced Development Guide

The documentation mainly targets advanced developers who require modifications and customization of the service. It supports downloading model deployments from modelscope and also supports deploying models that users have fine-tuned. For detailed information, please refer to the documentation available by docs