Whisper Medium Snamol
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 3.2500
- Wer: 385.7143
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: 32
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0 | 1000.0 | 1000 | 0.8347 | 31.4286 |
| 0.0 | 2000.0 | 2000 | 2.7926 | 542.8571 |
| 0.0 | 3000.0 | 3000 | 3.1362 | 631.4286 |
| 0.0 | 4000.0 | 4000 | 3.3433 | 391.4286 |
| 0.0 | 5000.0 | 5000 | 3.2500 | 385.7143 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 9
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-meduim-id-kp
Base model
openai/whisper-medium