Wav2vec2-CTC for AISHELL (Mandarin Chinese)

This repository provides all the necessary tools to perform automatic speech recognition from an end-to-end system pretrained on AISHELL (Mandarin Chinese) within SpeechBrain. For a better experience, we encourage you to learn more about SpeechBrain.

The performance of the model is the following:

Release	Dev CER	Test CER	GPUs	Full Results
20-09-22	4.48	5.02	1xRTX8000 48GB	Google Drive

Pipeline description

This ASR system is composed of 2 different but linked blocks:

Tokenizer (from huggingface) that transforms words into chars and trained with the training transcriptions of AISHELL-1.
Acoustic model made of a wav2vec2 encoder and fully-connected layers

To Train this system from scratch, see our SpeechBrain recipe.

The system is trained with recordings sampled at 16kHz (single channel).

Install SpeechBrain

First of all, please install SpeechBrain with the following command:

pip install speechbrain

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.

Transcribing your own audio files (in English)

from speechbrain.inference.interfaces import foreign_class
asr_model = foreign_class(source="speechbrain/asr-wav2vec2-ctc-aishell",  pymodule_file="custom_interface.py", classname="CustomEncoderDecoderASR")
asr_model.transcribe_file("speechbrain/asr-wav2vec2-ctc-aishell/example.wav")

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

Parallel Inference on a Batch

Please, see this Colab notebook to figure out how to transcribe in parallel a batch of input sentences using a pre-trained model.

Training

The model was trained with SpeechBrain (Commit hash: '480dde87'). To train it from scratch follow these steps:

Clone SpeechBrain:

git clone https://github.com/speechbrain/speechbrain.git

Install it:

cd speechbrain
pip install -r requirements.txt
pip install -e .

Run Training:

cd recipes/AISHELL-1/ASR/CTC/
python train_with_wav2vec.py hparams/train_with_wav2vec.yaml --data_folder=your_data_folder

You can find our training results (models, logs, etc) here.

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

About SpeechBrain

Website: https://speechbrain.github.io/
Code: https://github.com/speechbrain/speechbrain/
HuggingFace: https://huggingface.co/speechbrain/

Citing SpeechBrain

Please, cite SpeechBrain if you use it for your research or business.

@misc{speechbrain,
  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}