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

FunASR 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, 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

• FunASR supports many types of models, such as, Tranformer, Conformer, Paraformer.
• A large number of ASR models trained on academic datasets or industrial datasets are open sourced on ModelScope,
• The pretrained model Paraformer-large obtains the first place on many task in SpeechIO leaderboard
• FunASR supports large-scale dataset dataloader and multi-GPU training.

Installation(Training and Developing)

• Clone the repo:

git clone https://github.com/alibaba/FunASR.git

• Install Conda:

wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
sh Miniconda3-latest-Linux-x86_64.sh
conda create -n funasr python=3.7
conda activate funasr

• Install Pytorch (version >= 1.7.0):

cuda
9.2	conda install pytorch==1.7.0 torchvision==0.8.0 torchaudio==0.7.0 cudatoolkit=9.2 -c pytorch
10.2	conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=10.2 -c pytorch
11.1	conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=11.1 -c pytorch

For more versions, please see https://pytorch.org/get-started/locally

• Install ModelScope:

pip install "modelscope[audio]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

For more details about modelscope, please see modelscope installation

• Install FunASR and other packages:

pip install --editable ./

Pretrained model hub

We have trained many academic and industrial models, model hub

Contact

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

• email: funasr@list.alibaba-inc.com

• Dingding group:

Acknowledge

1. We borrowed a lot of code from Kaldi for data preparation.
2. We borrowed a lot of code from ESPnet. FunASR follows up the training and finetuning pipelines of ESPnet.
3. We referred Wenet for building dataloader for large scale data training.

License

This project is licensed under the The MIT License. FunASR also contains various third-party components and some code modified from other repos under other open source licenses.

Citations

@inproceedings{gao2020universal,
  title={Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model},
  author={Gao, Zhifu and Zhang, Shiliang and Lei, Ming and McLoughlin, Ian},
  booktitle={arXiv preprint arXiv:2010.14099},
  year={2020}
}

@inproceedings{gao2022paraformer,
  title={Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition},
  author={Gao, Zhifu and Zhang, Shiliang and McLoughlin, Ian and Yan, Zhijie},
  booktitle={INTERSPEECH},
  year={2022}
}