Asr Wav2vec2 Commonvoice 14 Zh CN

🚀 wav2vec 2.0 with CTC trained on CommonVoice Chinese(china) (No LM)

This repository offers all the essential tools for automatic speech recognition. It uses an end - to - end system pretrained on CommonVoice (Chinese Language) within SpeechBrain. For a better experience, we recommend learning more about SpeechBrain.

Model Information

Model Performance

The performance of the model is as follows:

Model Index

• Name: asr - wav2vec2 - commonvoice - 14 - zh - CN
  • Results:
    • Task:
      • Name: Automatic Speech Recognition
      • Type: automatic - speech - recognition
    • Dataset:
      • Name: CommonVoice Corpus 14.0 (Chinese(china))
      • Type: mozilla - foundation/common_voice_14.0
      • Config: zh - CN
      • Split: test
      • Args:
        • Language: zh - CN
    • Metrics:
      • Name: Test WER
      • Type: wer
      • Value: '16.68'

🚀 Quick Start

This repository provides all the necessary tools to perform automatic speech recognition from an end - to - end system pretrained on CommonVoice (Chinese Language) within SpeechBrain.

✨ Features

• This ASR system is composed of 2 different but linked blocks:
  • Tokenizer (unigram) that transforms words into unigrams and trained with the train transcriptions (train.tsv) of CommonVoice (zh - CN).
  • Acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model ([wav2vec2 - large - xlsr - 53](https://huggingface.co/facebook/wav2vec2 - large - xlsr - 53)) is combined with two DNN layers and finetuned on CommonVoice DE. The obtained final acoustic representation is given to the CTC decoder.
• The system is trained with recordings sampled at 16kHz (single channel). The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling transcribe_file if needed.

📦 Installation

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

pip install speechbrain transformers

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

💻 Usage Examples

Basic Usage

from speechbrain.inference.ASR import EncoderASR

asr_model = EncoderASR.from_hparams(source="speechbrain/asr - wav2vec2 - commonvoice - 14 - zh - CN", savedir="pretrained_models/asr - wav2vec2 - commonvoice - 14 - zh - CN")
asr_model.transcribe_file("speechbrain/asr - wav2vec2 - commonvoice - 14 - zh - CN/example - zh - CN.wav")

Advanced Usage

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.

🔧 Technical Details

Training

The model was trained with SpeechBrain. To train it from scratch follow these steps:

1. Clone SpeechBrain:

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

2. Install it:

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

3. Run Training:

cd recipes/CommonVoice/ASR/CTC/
python train_with_wav2vec.py hparams/train_zh - CN_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.

📄 License

This project is licensed under the apache - 2.0 license.

📚 Documentation

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}
}