CngFSt10sec_model
This model is a fine-tuned version of openai/whisper-medium on the Marcusxx/CngFSt10sec dataset. It achieves the following results on the evaluation set:
- Loss: 0.0450
- Cer: 37.7682
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: 16
- 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: 100
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0901 | 2.0661 | 250 | 0.1106 | 52.6468 |
| 0.0164 | 4.1322 | 500 | 0.0532 | 66.9124 |
| 0.0042 | 6.1983 | 750 | 0.0421 | 30.8922 |
| 0.0006 | 8.2645 | 1000 | 0.0433 | 30.8011 |
| 0.0005 | 10.3306 | 1250 | 0.0439 | 28.2827 |
| 0.0004 | 12.3967 | 1500 | 0.0445 | 32.2674 |
| 0.0004 | 14.4628 | 1750 | 0.0448 | 34.0485 |
| 0.0004 | 16.5289 | 2000 | 0.0450 | 37.7682 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for Marcusxx/CngFSt10sec_model
Base model
openai/whisper-medium