metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-a-norm-ls-5
results: []
whisper-a-norm-ls-5
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: 0.0448
- Wer: 184.1866
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: 0.0004
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use 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: 132
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 70 | 0.2880 | 157.4516 |
| 0.7821 | 2.0 | 140 | 0.0673 | 14.2207 |
| 0.1757 | 3.0 | 210 | 0.0536 | 175.0853 |
| 0.1757 | 4.0 | 280 | 0.0507 | 199.3174 |
| 0.0113 | 4.9353 | 345 | 0.0448 | 184.1866 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0