wav2vec2_phoneme_finetuned
This model is a fine-tuned version of facebook/wav2vec2-lv-60-espeak-cv-ft on the None dataset. It achieves the following results on the evaluation set:
- Loss: 68.3978
- Per: 0.1814
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Per |
|---|---|---|---|---|
| 268.9781 | 1.0 | 141 | 135.8863 | 0.2832 |
| 226.6022 | 2.0 | 282 | 101.9097 | 0.2148 |
| 198.0759 | 3.0 | 423 | 87.6582 | 0.1959 |
| 175.2407 | 4.0 | 564 | 80.1565 | 0.1944 |
| 168.0939 | 5.0 | 705 | 74.3647 | 0.1851 |
| 172.2129 | 6.0 | 846 | 70.7915 | 0.1866 |
| 159.1446 | 7.0 | 987 | 68.9037 | 0.1841 |
| 170.1425 | 8.0 | 1128 | 68.3978 | 0.1814 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2