Whisper Small ID - Kenn
This model is a fine-tuned version of openai/whisper-small on the Test Dataset 2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.6740
- Wer: 63.9241
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.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_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0008 | 41.6667 | 1000 | 1.5316 | 64.9789 |
| 0.0001 | 83.3333 | 2000 | 1.6316 | 64.3460 |
| 0.0 | 125.0 | 3000 | 1.6618 | 64.5570 |
| 0.0 | 166.6667 | 4000 | 1.6740 | 63.9241 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 107
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 kneth90/whisper-small-id
Base model
openai/whisper-small