speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

docs

Browse Source
This commit is contained in:
游雁 2023-11-08 16:31:22 +08:00
parent 323e43b485
commit fa3dbd8f28
2 changed files with 96 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

99
README.md
View File

@ -9,31 +9,32 @@
<a href=""><img src="https://img.shields.io/badge/Pytorch-%3E%3D1.11-blue"></a>
</p>
<strong>FunASR</strong> 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](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition), 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！
<strong>FunASR</strong> 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, 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！
[**Highlights**](#highlights)
| [**News**](https://github.com/alibaba-damo-academy/FunASR#whats-new)
| [**Installation**](#installation)
| [**Quick Start**](#quick-start)
| [**Runtime**](./runtime/readme.md)
| [**Model Zoo**](./docs/model_zoo/modelscope_models.md)
| [**Model Zoo**](#model-zoo)
| [**Contact**](#contact)
<a name="highlights"></a>
## Highlights
- FunASR is a fundamental speech recognition toolkit that offers a variety of features, including speech recognition (ASR), Voice Activity Detection (VAD), Punctuation Restoration, Language Models, Speaker Verification, Speaker Diarization and multi-talker ASR. FunASR provides convenient scripts and tutorials, supporting inference and fine-tuning of pre-trained models.
- We have released a vast collection of academic and industrial pretrained models on the [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition), which can be accessed through our [Model Zoo](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md). The representative [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary), a non-autoregressive end-to-end speech recognition model, has the advantages of high accuracy, high efficiency, and convenient deployment, supporting the rapid construction of speech recognition services. For more details on service deployment, please refer to the [service deployment document](funasr/runtime/readme_cn.md).
- We have released a vast collection of academic and industrial pretrained models on the [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition) and [huggingface](https://huggingface.co/FunASR), which can be accessed through our [Model Zoo](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md). The representative [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary), a non-autoregressive end-to-end speech recognition model, has the advantages of high accuracy, high efficiency, and convenient deployment, supporting the rapid construction of speech recognition services. For more details on service deployment, please refer to the [service deployment document](runtime/readme_cn.md).
<a name="whats-new"></a>
## What's new:
- 2023/10/17: The offline file transcription service (CPU) of English has been released. For more details, please refer to ([Deployment documentation](funasr/runtime/docs/SDK_tutorial_en.md)).
- 2023/11/08: The offline file transcription service 3.0 (CPU) of Mandarin has been released, adding punctuation large model, Ngram language model, and wfst hot words. For detailed information, please refer to [docs](runtime#file-transcription-service-mandarin-cpu).
- 2023/10/17: The offline file transcription service (CPU) of English has been released. For more details, please refer to ([docs](runtime#file-transcription-service-english-cpu)).
- 2023/10/13: [SlideSpeech](https://slidespeech.github.io/): A large scale multi-modal audio-visual corpus with a significant amount of real-time synchronized slides.
- 2023/10/10: The ASR-SpeakersDiarization combined pipeline [Paraformer-VAD-SPK](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr_vad_spk/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/demo.py) is now released. Experience the model to get recognition results with speaker information.
- 2023/10/07: [FunCodec](https://github.com/alibaba-damo-academy/FunCodec): A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec.
- 2023/09/01: The offline file transcription service 2.0 (CPU) of Mandarin has been released, with added support for ffmpeg, timestamp, and hotword models. For more details, please refer to ([Deployment documentation](funasr/runtime/docs/SDK_tutorial.md)).
- 2023/08/07: The real-time transcription service (CPU) of Mandarin has been released. For more details, please refer to ([Deployment documentation](funasr/runtime/docs/SDK_tutorial_online.md)).
- 2023/09/01: The offline file transcription service 2.0 (CPU) of Mandarin has been released, with added support for ffmpeg, timestamp, and hotword models. For more details, please refer to ([docs](runtime#file-transcription-service-mandarin-cpu)).
- 2023/08/07: The real-time transcription service (CPU) of Mandarin has been released. For more details, please refer to ([docs](runtime#the-real-time-transcription-service-mandarin-cpu)).
- 2023/07/17: BAT is released, which is a low-latency and low-memory-consumption RNN-T model. For more details, please refer to ([BAT](egs/aishell/bat)).
- 2023/06/26: ASRU2023 Multi-Channel Multi-Party Meeting Transcription Challenge 2.0 completed the competition and announced the results. For more details, please refer to ([M2MeT2.0](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)).
@ -43,17 +44,87 @@
Please ref to [installation docs](https://alibaba-damo-academy.github.io/FunASR/en/installation/installation.html)
## Deployment Service
## Model Zoo
FunASR has open-sourced a large number of pre-trained models on industrial data. You are free to use, copy, modify, and share FunASR models under the [Model License Agreement](./MODEL_LICENSE). Below are some representative models, for more models please refer to the [Model Zoo]().
FunASR supports pre-trained or further fine-tuned models for deployment as a service. The CPU version of the Chinese offline file conversion service has been released, details can be found in [docs](funasr/runtime/docs/SDK_tutorial.md). More detailed information about service deployment can be found in the [deployment roadmap](funasr/runtime/readme_cn.md).
(Note: 🤗 represents the Huggingface model zoo link, ⭐ represents the ModelScope model zoo link)
| Model Name | Task Details | Training Date | Parameters |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------:|:--------------------------------:|:----------:|
| paraformer-zh ([⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [🤗]() ) | speech recognition, with timestamps, non-streaming | 60000 hours, Mandarin | 220M |
| paraformer-zh-spk ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [🤗]() ) | speech recognition with speaker diarization, with timestamps, non-streaming | 60000 hours, Mandarin | 220M |
| paraformer-zh-online ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() ) | speech recognition, non-streaming | 60000 hours, Mandarin | 220M |
| paraformer-en ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() ) | speech recognition, with timestamps, non-streaming | 50000 hours, English | 220M |
| paraformer-en-spk ([🤗]() [⭐]() ) | speech recognition with speaker diarization, non-streaming | 50000 hours, English | 220M |
| conformer-en ( [⭐](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [🤗]() ) | speech recognition, non-streaming | 50000 hours, English | 220M |
| ct-punc ( [⭐](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗]() ) | punctuation restoration | 100M, Mandarin and English | 1.1G |
| fsmn-vad ( [⭐](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗]() ) | voice activity detection | 5000 hours, Mandarin and English | 0.4M |
| fa-zh ( [⭐](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [🤗]() ) | timestamp prediction | 5000 hours, Mandarin | 38M |
[//]: # ()
[//]: # (FunASR supports pre-trained or further fine-tuned models for deployment as a service. The CPU version of the Chinese offline file conversion service has been released, details can be found in [docs]&#40;funasr/runtime/docs/SDK_tutorial.md&#41;. More detailed information about service deployment can be found in the [deployment roadmap]&#40;funasr/runtime/readme_cn.md&#41;.)
<a name="quick-start"></a>
## Quick Start
Quick start for new users（[tutorial](https://alibaba-damo-academy.github.io/FunASR/en/funasr/quick_start.html)）
FunASR supports inference and fine-tuning of models trained on industrial data for tens of thousands of hours. For more details, please refer to [modelscope_egs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html). It also supports training and fine-tuning of models on academic standard datasets. For more information, please refer to [egs](https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html).
Below is a quick start tutorial. Test audio files ([Mandarin](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav), [English]()).
### Speech Recognition (Non-streaming)
```python
from funasr import infer
p = infer(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", model_hub="ms")
res = p("asr_example_zh.wav", batch_size_token=5000)
print(res)
```
Note: `model_hub`: represents the model repository, `ms` stands for selecting ModelScope download, `hf` stands for selecting Huggingface download.
### Speech Recognition (Streaming)
```python
from funasr import infer
p = infer(model="paraformer-zh-streaming", model_hub="ms")
chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, "encoder_chunk_look_back": 4, "decoder_chunk_look_back": 1}
import torchaudio
speech = torchaudio.load("asr_example_zh.wav")[0][0]
speech_length = speech.shape[0]
stride_size = chunk_size[1] * 960
sample_offset = 0
for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
param_dict["is_final"] = True if sample_offset + stride_size >= speech_length - 1 else False
input = speech[sample_offset: sample_offset + stride_size]
rec_result = p(input=input, param_dict=param_dict)
print(rec_result)
```
Note: `chunk_size` is the configuration for streaming latency.` [0,10,5]` indicates that the real-time display granularity is `10*60=600ms`, and the lookahead information is `5*60=300ms`. Each inference input is `600ms` (sample points are `16000*0.6=960`), and the output is the corresponding text. For the last speech segment input, `is_final=True` needs to be set to force the output of the last word.
Quick start for new users can be found in [docs](https://alibaba-damo-academy.github.io/FunASR/en/funasr/quick_start_zh.html)
[//]: # (FunASR supports inference and fine-tuning of models trained on industrial datasets of tens of thousands of hours. For more details, please refer to &#40;[modelscope_egs]&#40;https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html&#41;&#41;. It also supports training and fine-tuning of models on academic standard datasets. For more details, please refer to&#40;[egs]&#40;https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html&#41;&#41;. The models include speech recognition &#40;ASR&#41;, speech activity detection &#40;VAD&#41;, punctuation recovery, language model, speaker verification, speaker separation, and multi-party conversation speech recognition. For a detailed list of models, please refer to the [Model Zoo]&#40;https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md&#41;:)
## Deployment Service
FunASR supports deploying pre-trained or further fine-tuned models for service. Currently, it supports the following types of service deployment:
- File transcription service, Mandarin, CPU version, done
- The real-time transcription service, Mandarin (CPU), done
- File transcription service, English, CPU version, done
- File transcription service, Mandarin, GPU version, in progress
- and more.
For more detailed information, please refer to the [service deployment documentation](runtime/readme.md).
FunASR supports inference and fine-tuning of models trained on industrial datasets of tens of thousands of hours. For more details, please refer to ([modelscope_egs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html)). It also supports training and fine-tuning of models on academic standard datasets. For more details, please refer to([egs](https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html)). The models include speech recognition (ASR), speech activity detection (VAD), punctuation recovery, language model, speaker verification, speaker separation, and multi-party conversation speech recognition. For a detailed list of models, please refer to the [Model Zoo](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md):
<a name="Community Communication"></a>
## Community Communication
@ -67,8 +138,8 @@ You can also scan the following DingTalk group or WeChat group QR code to join t
## Contributors
| <div align="left"><img src="docs/images/damo.png" width="180"/> | <div align="left"><img src="docs/images/nwpu.png" width="260"/> | <img src="docs/images/China_Telecom.png" width="200"/> </div> | <img src="docs/images/RapidAI.png" width="200"/> </div> | <img src="docs/images/aihealthx.png" width="200"/> </div> | <img src="docs/images/XVERSE.png" width="250"/> </div> |
|:---------------------------------------------------------------:|:---------------------------------------------------------------:|:--------------------------------------------------------------:|:-------------------------------------------------------:|:-----------------------------------------------------------:|:------------------------------------------------------:|
| <div align="left"><img src="docs/images/nwpu.png" width="260"/> | <img src="docs/images/China_Telecom.png" width="200"/> </div> | <img src="docs/images/RapidAI.png" width="200"/> </div> | <img src="docs/images/aihealthx.png" width="200"/> </div> | <img src="docs/images/XVERSE.png" width="250"/> </div> |
|:---------------------------------------------------------------:|:--------------------------------------------------------------:|:-------------------------------------------------------:|:-----------------------------------------------------------:|:------------------------------------------------------:|
The contributors can be found in [contributors list](./Acknowledge.md)
@ -91,12 +162,6 @@ The use of pretraining model is subject to [model license](./MODEL_LICENSE)
year={2023},
booktitle={INTERSPEECH},
}
@inproceedings{wang2023told,
author={Jiaming Wang and Zhihao Du and Shiliang Zhang},
title={{TOLD:} {A} Novel Two-Stage Overlap-Aware Framework for Speaker Diarization},
year={2023},
booktitle={ICASSP},
}
@inproceedings{gao22b_interspeech,
author={Zhifu Gao and ShiLiang Zhang and Ian McLoughlin and Zhijie Yan},
title={{Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition}},

27
README_zh.md
View File

@ -18,7 +18,7 @@ FunASR希望在语音识别的学术研究和工业应用之间架起一座桥
｜<a href="#安装教程"> 安装 </a>
｜<a href="#快速开始"> 快速开始 </a>
｜<a href="https://alibaba-damo-academy.github.io/FunASR/en/index.html"> 教程文档 </a>
｜<a href="./docs/model_zoo/modelscope_models.md"> 模型仓库 </a>
｜<a href="#模型仓库"> 模型仓库 </a>
｜<a href="#服务部署"> 服务部署 </a>
｜<a href="#联系我们"> 联系我们 </a>
</h4>
@ -27,10 +27,11 @@ FunASR希望在语音识别的学术研究和工业应用之间架起一座桥
<a name="核心功能"></a>
## 核心功能
- FunASR是一个基础语音识别工具包，提供多种功能，包括语音识别（ASR）、语音端点检测（VAD）、标点恢复、语言模型、说话人验证、说话人分离和多人对话语音识别等。FunASR提供了便捷的脚本和教程，支持预训练好的模型的推理与微调。
- 我们在[ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition)与[huggingface](https://huggingface.co/FunAudio)上发布了大量开源数据集或者海量工业数据训练的模型，可以通过我们的[模型仓库](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md)了解模型的详细信息。代表性的[Paraformer](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)非自回归端到端语音识别模型具有高精度、高效率、便捷部署的优点，支持快速构建语音识别服务，详细信息可以阅读([服务部署文档](funasr/runtime/readme_cn.md))。
- 我们在[ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition)与[huggingface](https://huggingface.co/FunASR)上发布了大量开源数据集或者海量工业数据训练的模型，可以通过我们的[模型仓库](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md)了解模型的详细信息。代表性的[Paraformer](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)非自回归端到端语音识别模型具有高精度、高效率、便捷部署的优点，支持快速构建语音识别服务，详细信息可以阅读([服务部署文档](runtime/readme_cn.md))。
<a name="最新动态"></a>
## 最新动态
- 2023/11/08：中文离线文件转写服务3.0 CPU版本发布，新增标点大模型、Ngram语言模型与wfst热词，详细信息参阅([一键部署文档](runtime/readme_cn.md#中文离线文件转写服务cpu版本))
- 2023/10/17: 英文离线文件转写服务一键部署的CPU版本发布，详细信息参阅([一键部署文档](runtime/readme_cn.md#英文离线文件转写服务cpu版本))
- 2023/10/13: [SlideSpeech](https://slidespeech.github.io/): 一个大规模的多模态音视频语料库，主要是在线会议或者在线课程场景，包含了大量与发言人讲话实时同步的幻灯片。
- 2023.10.10: [Paraformer-long-Spk](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr_vad_spk/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/demo.py)模型发布，支持在长语音识别的基础上获取每句话的说话人标签。
@ -51,17 +52,17 @@ FunASR开源了大量在工业数据上预训练模型，您可以在[模型许
（注：[🤗]()表示Huggingface模型仓库链接，[⭐]()表示ModelScope模型仓库链接）
| 模型名字 | 任务详情 | 训练数据 | 参数量 |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------:|:------------:|:----:|
| paraformer-zh ([⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [🤗]() ) | 语音识别，带时间戳输出，非实时 | 60000小时，中文 | 220M |
| paraformer-zh-spk ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) ) | 分角色语音识别，带时间戳输出，非实时 | 60000小时，中文 | 220M |
| paraformer-zh-online ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() ) | 语音识别，实时 | 60000小时，中文 | 220M |
| paraformer-en ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() ) | 分角色语音识别，带时间戳输出，非实时 | 50000小时，英文 | 220M |
| paraformer-en-spk ([🤗]() [⭐]() ) | 语音识别，非实时 | 50000小时，英文 | 220M |
| conformer-en ( [⭐](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [🤗]() ) | 语音识别，非实时 | 50000小时，英文 | 220M |
| ct-punc ( [⭐](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗]() ) | 标点恢复，非实时 | 100M，中文与英文 | 1.1G |
| fsmn-vad ( [⭐](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗]() ) | 语音端点检测，实时 | 5000小时，中文与英文 | 0.4M |
| fa-zh ( [⭐](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [🤗]() ) | 字级别时间戳预测 | 50000小时，中文 | 38M |
| 模型名字 | 任务详情 | 训练数据 | 参数量 |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------:|:------------:|:----:|
| paraformer-zh ([⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [🤗]() ) | 语音识别，带时间戳输出，非实时 | 60000小时，中文 | 220M |
| paraformer-zh-spk ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [🤗]() ) | 分角色语音识别，带时间戳输出，非实时 | 60000小时，中文 | 220M |
| paraformer-zh-online ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() ) | 语音识别，实时 | 60000小时，中文 | 220M |
| paraformer-en ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() ) | 语音识别，非实时 | 50000小时，英文 | 220M |
| paraformer-en-spk ([🤗]() [⭐]() ) | 语音识别，非实时 | 50000小时，英文 | 220M |
| conformer-en ( [⭐](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [🤗]() ) | 语音识别，非实时 | 50000小时，英文 | 220M |
| ct-punc ( [⭐](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗]() ) | 标点恢复 | 100M，中文与英文 | 1.1G |
| fsmn-vad ( [⭐](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗]() ) | 语音端点检测，实时 | 5000小时，中文与英文 | 0.4M |
| fa-zh ( [⭐](https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [🤗]() ) | 字级别时间戳预测 | 50000小时，中文 | 38M |
<a name="快速开始"></a>