AlexN
/

xls-r-300m-fr

Automatic Speech Recognition Transformers PyTorch

French wav2vec2 generated_from_trainer hf-asr-leaderboard mozilla-foundation/common_voice_8_0 robust-speech-event Eval Results Inference Endpoints

Model card Files Files and versions Community

Edit model card

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - FR dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2700
num_epochs: 1.0
mixed_precision_training: Native AMP

Framework versions

Transformers 4.17.0.dev0
Pytorch 1.10.2+cu102
Datasets 1.18.2.dev0
Tokenizers 0.11.0

Downloads last month: 12

Dataset used to train AlexN/xls-r-300m-fr

Evaluation results

Test WER on Common Voice 8.0 fr
self-reported

21.580
Test WER on Robust Speech Event - Dev Data
self-reported

36.030
Test WER on Robust Speech Event - Test Data
self-reported

38.860

View on Papers With Code