metadata
language: fr
thumbnail: null
tags:
- automatic-speech-recognition
- wav2vec2
license: apache-2.0
LeBenchmark: wav2vec2 large model training on 3K hours of French speech
Some text
description
Some text
Intended uses & limitations
Some text
Fine-tune with Fairseq (ASR with CTC)
Instructions
pip install fairseq
Integrate to SpeechBrain (ASR, SLU, Speaker ...)
Referencing LeBenchmark