Hugging Face's logo

jonatasgrosman
/
wav2vec2-large-xlsr-53-french

Automatic Speech Recognition Transformers PyTorch JAX
French wav2vec2 audio hf-asr-leaderboard mozilla-foundation/common_voice_6_0 robust-speech-event speech xlsr-fine-tuning-week Eval Results Inference Endpoints
Model card Files Community
3

Kenlm language model

#1
by GaetanBaert - opened
Discussion
GaetanBaert

Hello,
Which dataset did you use to train the Kenlm model ?
Also, what parameters did you use ?

jonatasgrosman
 Owner

Hello @GaetanBaert ! To build the LM, I've used the data from Common Voice 8.0, MediaSpeech, Multilingual TEDx, Multilingual LibriSpeech, and Voxpopuli. I've transformed all the text to lowercase and removed the punctuation.

Sign up or log in to comment