test_whisper
This model is a fine-tuned version of openai/whisper-base on the mangoo111/2025re_learn dataset. It achieves the following results on the evaluation set:
- Loss: 1.5861
- Cer: 26.9608
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: 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0001 | 500.0 | 1000 | 1.4129 | 26.9608 |
| 0.0001 | 1000.0 | 2000 | 1.5120 | 28.4314 |
| 0.0 | 1500.0 | 3000 | 1.5603 | 26.9608 |
| 0.0 | 2000.0 | 4000 | 1.5861 | 26.9608 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
- Datasets 2.17.1
- Tokenizers 0.21.0
- Downloads last month
- 2
Model tree for mangoo111/2025re_learn
Base model
openai/whisper-base