metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: output_dir
results: []
output_dir
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: 2.2254
- Wer: 106.2847
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 1.9269 | 1.0152 | 1000 | 1.9970 | 98.8909 |
| 1.1741 | 2.0305 | 2000 | 1.9986 | 98.7061 |
| 0.5248 | 3.0457 | 3000 | 2.0790 | 102.4030 |
| 0.2094 | 4.0609 | 4000 | 2.1701 | 104.2514 |
| 0.086 | 5.0761 | 5000 | 2.2254 | 106.2847 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1