Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper-medium-new
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0014
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: 0.001
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1198 | 1.0 | 137 | 0.1716 |
| 0.0915 | 2.0 | 274 | 0.1142 |
| 0.0769 | 3.0 | 411 | 0.0448 |
| 0.0444 | 4.0 | 548 | 0.0345 |
| 0.0439 | 5.0 | 685 | 0.0209 |
| 0.0175 | 6.0 | 822 | 0.0110 |
| 0.0136 | 7.0 | 959 | 0.0079 |
| 0.0067 | 8.0 | 1096 | 0.0031 |
| 0.0024 | 9.0 | 1233 | 0.0017 |
| 0.0015 | 10.0 | 1370 | 0.0014 |
Framework versions
- PEFT 0.8.0
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for nrshoudi/Whisper-medium-new
Base model
openai/whisper-medium