Whisper Small custom 3000
This model is a fine-tuned version of openai/whisper-small on the lyhourt/clean dataset. It achieves the following results on the evaluation set:
- Loss: 0.0304
- Wer: 4.6902
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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 300
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0783 | 0.3333 | 100 | 0.0938 | 11.8124 |
| 0.0513 | 0.6667 | 200 | 0.0689 | 8.2224 |
| 0.0027 | 1.19 | 300 | 0.0304 | 4.6902 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 18
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for lyhourt/whisper-small-custom-300
Base model
openai/whisper-small