wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the xtreme_s dataset. It achieves the following results on the evaluation set:
- Loss: 2.1819
- Wer: 1.0
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: 0.0005
- 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: 200
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.236 | 6.15 | 100 | 2.9095 | 1.0 |
| 2.8926 | 12.31 | 200 | 2.8601 | 1.0 |
| 2.871 | 18.46 | 300 | 2.8546 | 1.0 |
| 2.763 | 24.62 | 400 | 2.1819 | 1.0 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1