metadata
language:
- fr
license: apache-2.0
tags:
- automatic-speech-recognition
- mozilla-foundation/common_voice_7_0
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: ''
results: []
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - FR dataset. It achieves the following results on the evaluation set:
- Loss: 0.5417
- Wer: 0.4479
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: 7.5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 0.2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.9106 | 0.04 | 500 | 6.7171 | 1.0 |
| 3.0034 | 0.08 | 1000 | 3.0126 | 1.0 |
| 2.8699 | 0.12 | 1500 | 2.8509 | 0.9817 |
| 1.629 | 0.16 | 2000 | 0.7787 | 0.5861 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2.dev0
- Tokenizers 0.11.0