metadata

language: fr
thumbnail: null
tags:
  - ASR
  - CTC
  - Attention
  - pytorch
license: apache-2.0
datasets:
  - commonvoice
metrics:
  - wer
  - cer

CRDNN with CTC/Attention trained on CommonVoice French (No LM)

This repository provides all the necessary tools to perform automatic speech recognition from an end-to-end system pretrained on CommonVoice (FR) within SpeechBrain. For a better experience, we encourage you to learn more about SpeechBrain. The given ASR model performance are:

Release	Test CER	Test WER	GPUs
07-03-21	6.54	17.70	2xV100 16GB

Pipeline description

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

Tokenizer (unigram) that transforms words into subword units and trained with the train transcriptions (train.tsv) of CommonVoice (FR).
Acoustic model (CRDNN + CTC/Attention). The CRDNN architecture is made of N blocks of convolutional neural networks with normalization and pooling on the frequency domain. Then, a bidirectional LSTM is connected to a final DNN to obtain the final acoustic representation that is given to the CTC and attention decoders.

Intended uses & limitations

This model has been primarily developed to be run within SpeechBrain as a pretrained ASR model for the French language. Thanks to the flexibility of SpeechBrain, any of the 2 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

from speechbrain.pretrained import EncoderDecoderASR

asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-commonvoice-fr")
asr_model.transcribe_file("path_to_your_file.wav")

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}},
  }