|
--- |
|
language: "fr" |
|
thumbnail: |
|
tags: |
|
- ASR |
|
- CTC |
|
- Attention |
|
- pytorch |
|
- speechbrain |
|
- Transformer |
|
license: "apache-2.0" |
|
datasets: |
|
- commonvoice |
|
metrics: |
|
- wer |
|
- cer |
|
--- |
|
|
|
# wav2vec 2.0 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 (French Language) within |
|
SpeechBrain. For a better experience, we encourage you to learn more about |
|
[SpeechBrain](https://speechbrain.github.io). The given ASR model performance are: |
|
|
|
| Release | Test CER | Test WER | GPUs | |
|
|:-------------:|:--------------:|:--------------:| :--------:| |
|
| 29-04-21 | 9.62 | 13.90 | 2xV100 32GB | |
|
|
|
## 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 (train.tsv) of CommonVoice (FR). |
|
3. Acoustic model (wav2vec2.0 + CTC/Attention). A pretrained wav2vec 2.0 model ([wav2vec2-large-xlsr-53-french](https://huggingface.co/facebook/wav2vec2-large-xlsr-53-french)) is combined with two DNN layers and finetuned on CommonVoice FR. |
|
The obtained final acoustic representation 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 tranformers 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](https://speechbrain.github.io). |
|
|
|
### Transcribing your own audio files (in French) |
|
|
|
```python |
|
from speechbrain.pretrained import EncoderDecoderASR |
|
|
|
asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-commonvoice-fr", savedir="pretrained_models/asr-crdnn-commonvoice-fr") |
|
asr_model.transcribe_file("example-fr.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}}, |
|
} |
|
``` |
|
|
