wav2vec2_common_voice17_finetuning
This model is a fine-tuned version of facebook/wav2vec2-base on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4054
- 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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6577 | 3.5461 | 1000 | 0.4788 | 0.9997 |
| 0.2893 | 7.0922 | 2000 | 0.4086 | 1.0 |
| 0.1997 | 10.6383 | 3000 | 0.4135 | 0.9997 |
| 0.156 | 14.1844 | 4000 | 0.4051 | 0.9992 |
| 0.138 | 17.7305 | 5000 | 0.4054 | 1.0 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.4.1+cu124
- Datasets 2.21.0
- Tokenizers 0.21.0