speechbrainteam's picture
Update README.md
c866673
|
raw
history blame
3.34 kB
metadata
language: en
thumbnail: null
tags:
  - ASR
  - CTC
  - Attention
  - Transformers
  - pytorch
license: apache-2.0
datasets:
  - aishell
metrics:
  - wer
  - cer

Transformer 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 given ASR model performance are:

Release Dev CER Test CER GPUs Full Results
05-03-21 5.60 6.04 2xV100 32GB Google Drive

Pipeline description

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

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

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

Intended uses & limitations

This model has been primarily developed to be run within SpeechBrain as a pretrained ASR model for the Mandarin Chinese language. Thanks to the flexibility of SpeechBrain, any of the 3 blocks detailed above can be extracted and connected to your custom pipeline as long as SpeechBrain is installed.

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.pretrained 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.wav")

Inference on GPU

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

Referencing SpeechBrain

@misc{SB2021,
    author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
    title = {SpeechBrain},
    year = {2021},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\url{https://github.com/speechbrain/speechbrain}},
  }

About SpeechBrain

SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains. Website: https://speechbrain.github.io/ GitHub: https://github.com/speechbrain/speechbrain