Asr Transformer Aishell

🚀 Transformer for AISHELL (Mandarin Chinese)

This repository offers all essential tools for automatic speech recognition within SpeechBrain, using an end - to - end system pretrained on AISHELL (Mandarin Chinese). For a better experience, explore SpeechBrain.

The performance of the model is as follows:

🚀 Quick Start

This ASR system consists of two different yet linked blocks:

• Tokenizer (unigram) that transforms words into subword units and is trained with the train transcriptions of LibriSpeech.
• Acoustic model made of a transformer encoder and a joint decoder with CTC + transformer. Thus, the decoding also incorporates the CTC probabilities.

To train this system from scratch, [see our SpeechBrain recipe](https://github.com/speechbrain/speechbrain/tree/develop/recipes/AISHELL - 1).

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.

✨ Features

• End - to - end ASR: Perform automatic speech recognition on Mandarin Chinese using a pre - trained model.
• Flexible Decoding: Incorporate CTC probabilities in the decoding process.
• Audio Normalization: Automatically normalize audio during transcription.

📦 Installation

First, install SpeechBrain with the following command:

pip install speechbrain

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

💻 Usage Examples

Basic Usage

from speechbrain.inference.ASR import EncoderDecoderASR

asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-transformer-aishell", savedir="pretrained_models/asr-transformer-aishell")
asr_model.transcribe_file("speechbrain/asr-transformer-aishell/example_mandarin2.flac")

Advanced Usage

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

Parallel Inference on a Batch

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

Training

The model was trained with SpeechBrain (Commit hash: '986a2175'). 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/AISHELL-1/ASR/transformer/
python train.py hparams/train_ASR_transformer.yaml --data_folder=your_data_folder

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

Limitations

⚠️ Important Note

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

📚 Documentation

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

📄 License

This project is licensed under the "apache - 2.0" license.

📚 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}
}