wenet
v3.1.0
路線圖|文檔|論文|運行時|預驗證的模型|擁抱面|問威內特大師
我們共享網絡。
pip install git+https://github.com/wenet-e2e/wenet.git命令行的用法(參數使用-h ):
wenet --language chinese audio.wavPython編程用法:
import wenet
model = wenet . load_model ( 'chinese' )
result = model . transcribe ( 'audio.wav' )
print ( result [ 'text' ])請參閱Python使用情況以獲取更多命令行和Python編程用法。
git clone https://github.com/wenet-e2e/wenet.gitconda create -n wenet python=3.10
conda activate wenet
conda install conda-forge::soxpip install torch==2.2.2+cu121 torchaudio==2.2.2+cu121 -f https://download.pytorch.org/whl/torch_stable.html安裝CANN:請關注此鏈接以安裝CANN TOOLKIT和內核。
安裝具有Torch-NPU依賴性的WENET:
pip install -e .[torch-npu]| 要求 | 最低限度 | 推薦 |
|---|---|---|
| 坎恩 | 8.0.rc2.alpha003 | 最新的 |
| 火炬 | 2.1.0 | 2.2.0 |
| TORCH-NPU | 2.1.0 | 2.2.0 |
| Torchaudio | 2.1.0 | 2.2.0 |
| 深速 | 0.13.2 | 最新的 |
pip install -r requirements.txt
pre-commit install # for clean and tidy code # If you encounter sox compatibility issues
RuntimeError: set_buffer_size requires sox extension which is not available.
# ubuntu
sudo apt-get install sox libsox-dev
# centos
sudo yum install sox sox-devel
# conda env
conda install conda-forge::sox構建部署
可選地,如果要使用X86運行時或語言模型(LM),則必須如下構建運行時。否則,您可以忽略此步驟。
# runtime build requires cmake 3.14 or above
cd runtime/libtorch
mkdir build && cd build && cmake -DGRAPH_TOOLS=ON .. && cmake --build .請參閱DOC,以便在更多平台和操作系統上構建運行時間。
您可以直接討論GitHub問題。
對於中國用戶,您還可以在左側掃描QR碼,以遵循我們的官方帳戶。我們創建了一個微信小組,以進行更好的討論和更快的響應。請在右側掃描個人QR碼,該人負責邀請您參加聊天組。
![]() | ![]() |
|---|
@inproceedings { yao2021wenet ,
title = { WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit } ,
author = { Yao, Zhuoyuan and Wu, Di and Wang, Xiong and Zhang, Binbin and Yu, Fan and Yang, Chao and Peng, Zhendong and Chen, Xiaoyu and Xie, Lei and Lei, Xin } ,
booktitle = { Proc. Interspeech } ,
year = { 2021 } ,
address = { Brno, Czech Republic } ,
organization = { IEEE }
}
@article { zhang2022wenet ,
title = { WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit } ,
author = { Zhang, Binbin and Wu, Di and Peng, Zhendong and Song, Xingchen and Yao, Zhuoyuan and Lv, Hang and Xie, Lei and Yang, Chao and Pan, Fuping and Niu, Jianwei } ,
journal = { arXiv preprint arXiv:2203.15455 } ,
year = { 2022 }
}