Buckets:
809 MB
11 files
Updated 26 days ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| .gitattributes | 1.52 kB xet | 818ba6de | |
| README.md | 2.04 kB xet | 3f8291c3 | |
| config.json | 1.44 kB xet | 858f79ab | |
| generation_config.json | 364 Bytes xet | abe58555 | |
| merges.txt | 1.33 kB xet | 057ceded | |
| model.safetensors | 809 MB xet | abfbb8c1 | |
| preprocessor_config.json | 356 Bytes xet | b3037bdb | |
| special_tokens_map.json | 700 Bytes xet | f901f6e4 | |
| tokenizer_config.json | 1.9 kB xet | f5cb91b7 | |
| trainer_state.json | 35.7 kB xet | cba8e3b5 | |
| vocab.json | 6.76 kB xet | 198e24f7 |
GAL500
This model is a fine-tuned version of openai/whisper-small on the Enpas/GALKG dataset. It achieves the following results on the evaluation set:
- Loss: 0.2507
- Wer: 25.2114
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: 5e-05
- train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.5194 | 0.3199 | 1000 | 0.4919 | 45.8570 |
| 0.4237 | 0.6398 | 2000 | 0.3681 | 37.4251 |
| 0.349 | 0.9597 | 3000 | 0.3047 | 30.5457 |
| 0.2235 | 1.2796 | 4000 | 0.2758 | 27.5404 |
| 0.188 | 1.5995 | 5000 | 0.2507 | 25.2114 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.1
- Total size
- 809 MB
- Files
- 11
- Last updated
- Jun 12
- Pre-warmed CDN
- US EU US EU