Multilingual_xlsr-128_F4_New
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8277
- Accuracy: 0.8057
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9593 | 0.5714 | 400 | 1.0262 | 0.5600 |
| 0.3676 | 1.1429 | 800 | 0.8822 | 0.6379 |
| 0.8912 | 1.7143 | 1200 | 0.8460 | 0.6864 |
| 1.1383 | 2.2857 | 1600 | 0.8298 | 0.7136 |
| 0.2876 | 2.8571 | 2000 | 0.7253 | 0.7521 |
| 0.3098 | 3.4286 | 2400 | 0.6343 | 0.7957 |
| 0.4108 | 4.0 | 2800 | 0.6243 | 0.7971 |
| 0.7835 | 4.5714 | 3200 | 0.7857 | 0.7614 |
| 0.8907 | 5.1429 | 3600 | 0.8595 | 0.7714 |
| 0.4146 | 5.7143 | 4000 | 0.7092 | 0.7857 |
| 0.6735 | 6.2857 | 4400 | 0.6904 | 0.8150 |
| 0.6409 | 6.8571 | 4800 | 0.6908 | 0.8121 |
| 0.6568 | 7.4286 | 5200 | 0.8046 | 0.8036 |
| 0.1056 | 8.0 | 5600 | 0.7903 | 0.8079 |
| 0.2654 | 8.5714 | 6000 | 0.8277 | 0.8057 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1