model_20231101
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0472
- Wer: 285.6269
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: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 6000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1216 | 8.99 | 1000 | 1.0660 | 407.7217 |
| 0.0077 | 17.98 | 2000 | 1.0201 | 287.1560 |
| 0.0003 | 26.97 | 3000 | 1.0195 | 260.5505 |
| 0.0002 | 35.96 | 4000 | 1.0347 | 286.2385 |
| 0.0001 | 44.94 | 5000 | 1.0430 | 275.3058 |
| 0.0001 | 53.93 | 6000 | 1.0472 | 285.6269 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for lw2333/test
Base model
openai/whisper-small