ASR_Ascend_Whisper
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5906
- Wer: 107.3292
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 16
- 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: 100
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2465 | 1.6181 | 500 | 0.5249 | 114.4410 |
| 0.0871 | 3.2362 | 1000 | 0.5664 | 105.5280 |
| 0.0494 | 4.8544 | 1500 | 0.5906 | 107.3292 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1
- Downloads last month
- 4
Model tree for whismyswift/ASR_Ascend_Whisper
Base model
openai/whisper-small