Merge pull request #46 from alibaba-damo-academy/main

zhifu gao

2023-01-30 a26818d69c1808c5ab8be8cfeddc61ec3cd96fde

Merge pull request #46 from alibaba-damo-academy/main

merge

 README.md

@@ -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)
@@ -61,18 +62,14 @@
pip install --editable ./
```

## Pretrained Model Zoo

We have trained many academic and industrial models, [model hub](docs/modelscope_models.md)

## Contact

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

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


## Acknowledge

 docs/images/.DS_Store

Binary files differ

 docs/images/wechat.png

 funasr/bin/asr_inference_paraformer_vad_punc.py

@@ -3,6 +3,7 @@
import logging
import sys
import time
import json
from pathlib import Path
from typing import Optional
from typing import Sequence
@@ -637,8 +638,9 @@
                                                                                   postprocessed_result[2]
                        if len(word_lists) > 0: 
                            text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
                            text_postprocessed_punc_time_stamp = "predictions: {}  time_stamp: {}".format(
                                text_postprocessed_punc, time_stamp_postprocessed)
                            text_postprocessed_punc_time_stamp = json.dumps({"predictions": text_postprocessed_punc,
                                                                             "time_stamp": time_stamp_postprocessed},
                                                                            ensure_ascii=False)
                        else:
                            text_postprocessed_punc = ""
                            punc_id_list = []