whisper-base.en-speech-commands-v1
This model is a fine-tuned version of openai/whisper-base.en on the speech_commands dataset. It achieves the following results on the evaluation set:
- Loss: 1.1638
- Accuracy: 0.8067
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: 5e-05
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 384
- 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_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3306 | 1.0 | 103 | 1.1388 | 0.8022 |
| 0.1314 | 2.0 | 206 | 1.1511 | 0.8022 |
| 0.0672 | 3.0 | 309 | 1.1448 | 0.8062 |
| 0.048 | 4.0 | 412 | 1.1638 | 0.8067 |
| 0.034 | 5.0 | 515 | 1.1655 | 0.8058 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1