docs

游雁

2023-04-17 9d2f783ff6c75b9f6925e674f09237067d508318

docs

 .gitignore

@@ -10,3 +10,6 @@
RapidASR
export/*
*.pyc
.eggs
MaaS-lib
.gitignore

 README.md

@@ -1,6 +1,11 @@
[//]: # (<div align="left"><img src="docs/images/funasr_logo.jpg" width="400"/></div>)

# FunASR: A Fundamental End-to-End Speech Recognition Toolkit
<p align="left">
    <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-brightgreen.svg"></a>
    <a href=""><img src="https://img.shields.io/badge/Python->=3.7,<=3.10-aff.svg"></a>
    <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！

@@ -20,7 +25,7 @@
For the release notes, please ref to [news](https://github.com/alibaba-damo-academy/FunASR/releases)

## Highlights
- Many types of typical models are supported, e.g., [Tranformer](https://arxiv.org/abs/1706.03762), [Conformer](https://arxiv.org/abs/2005.08100), [Paraformer](https://arxiv.org/abs/2206.08317).
- 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)
- 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)

 docs/installation.md

@@ -1,7 +1,13 @@
# Installation
FunASR is easy to install. The detailed installation steps are as follows:
<p align="left">
    <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-brightgreen.svg"></a>
    <a href=""><img src="https://img.shields.io/badge/Python->=3.7,<=3.10-aff.svg"></a>
    <a href=""><img src="https://img.shields.io/badge/Pytorch-%3E%3D1.11-blue"></a>
</p>

- Install Conda and create virtual environment:
## Installation

### Install Conda (Optional):

```sh
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
sh Miniconda3-latest-Linux-x86_64.sh
@@ -10,26 +16,38 @@
conda activate funasr
```

- Install Pytorch (version >= 1.7.0):
### Install Pytorch (version >= 1.11.0):

```sh
pip install torch torchaudio
```

For more versions, please see [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally)
For more details about torch, please see [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally)

- Install ModelScope
### Install funasr

For users in China, you can configure the following mirror source to speed up the downloading:
``` sh
pip config set global.index-url https://mirror.sjtu.edu.cn/pypi/web/simple
```
Install or update ModelScope
```sh
pip install "modelscope[audio_asr]" --upgrade -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
#### Install from pip

```shell
pip install -U funasr
# For the users in China, you could install with the command:
# pip install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
```

- Clone the repo and install other packages
### Or install from source code

``` sh
git clone https://github.com/alibaba/FunASR.git && cd FunASR
pip install --editable ./
pip install -e ./
# For the users in China, you could install with the command:
# pip install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple
```

### Install modelscope (Optional)
If you want to use the pretrained models in ModelScope, you should install the modelscope:

```shell
pip install -U modelscope
# For the users in China, you could install with the command:
# pip install -U modelscope -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple
```