metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: stammer-libristutter-small
results: []
stammer-libristutter-small
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: 0.4182
- Wer: 18.2373
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 32
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1664 | 0.25 | 8 | 0.9333 | 36.5739 |
| 0.7815 | 0.5 | 16 | 0.5958 | 20.2668 |
| 0.5303 | 0.75 | 24 | 0.4729 | 18.3225 |
| 0.4116 | 1.0 | 32 | 0.4182 | 18.2373 |
Framework versions
- Transformers 4.43.2
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1