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
- 42
Evaluation results
- Test WER on Common Voice 8.0 frself-reported21.580
- Test WER on Robust Speech Event - Dev Dataself-reported36.030
- Test WER on Robust Speech Event - Test Dataself-reported38.860