whisper-small-kdj
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: 0.3926
- Wer: 16.7456
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 2
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_8bit 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: 5
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0001 | 58.8615 | 1000 | 0.3926 | 16.7456 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.0
- Downloads last month
- 8
Model tree for Achuka/whisper-small-kdj
Base model
openai/whisper-small