Merge branch 'dev' of https://github.com/alibaba-damo-academy/FunASR into dev

speech_asr

2023-02-09 2c167ecef3421f1f5e876fd7c158f57faa1abceb

 README.md

@@ -2,7 +2,7 @@

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

<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！[Model Zoo](docs/modelscope_models.md)
<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！

## Release Notes: 
### 2023.1.16, funasr-0.1.6
@@ -23,7 +23,7 @@
- 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.

## Installation(Training and Developing)
## Installation

- Install Conda:
``` sh
@@ -40,16 +40,17 @@
```
For more versions, please see [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally)

- Install ModelScope:

If you are in the area of China, you could set the source to speed the downloading.
If you are in the area of China, you could set the source to speedup the downloading.

``` sh
pip config set global.index-url https://mirror.sjtu.edu.cn/pypi/web/simple
```

- Install ModelScope:
Install or upgrade modelscope.
``` sh
pip install "modelscope[audio]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
pip install "modelscope[audio]" --upgrade -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
```

For more details about modelscope, please see [modelscope installation](https://modelscope.cn/docs/%E7%8E%AF%E5%A2%83%E5%AE%89%E8%A3%85)
@@ -61,9 +62,8 @@
pip install --editable ./
```

## Pretrained Model Zoo

We have trained many academic and industrial models, [model hub](docs/modelscope_models.md)
## Usage
For users who are new to FunASR and ModelScope, please refer to [FunASR Docs](https://alibaba-damo-academy.github.io/FunASR/index.html).

## Contact

@@ -71,15 +71,21 @@

- email: [funasr@list.alibaba-inc.com](funasr@list.alibaba-inc.com)

- Dingding group:
<div align="left"><img src="docs/images/dingding.jpg" width="250"/>!<img src="docs/images/wechat.png" width="222"/></div>
|Dingding group | Wechat group|
|:---:|:---:|
|<div align="left"><img src="docs/images/dingding.jpg" width="250"/> |<img src="docs/images/wechat.png" width="222"/></div>|

## Contributors

| <div align="left"><img src="docs/images/DeepScience.png" width="250"/> |
|:---:|

## Acknowledge

1. We borrowed a lot of code from [Kaldi](http://kaldi-asr.org/) for data preparation.
2. We borrowed a lot of code from [ESPnet](https://github.com/espnet/espnet). FunASR follows up the training and finetuning pipelines of ESPnet.
3. We referred [Wenet](https://github.com/wenet-e2e/wenet) for building dataloader for large scale data training.
4. We acknowledge [DeepScience](https://www.deepscience.cn) for contributing the grpc service.

## License
This project is licensed under the [The MIT License](https://opensource.org/licenses/MIT). FunASR also contains various third-party components and some code modified from other repos under other open source licenses.