Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-cv16-1__car50-all-format_copy2x_voiceless-241204-v1
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0868
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.7803 | 1.0 | 93 | 2.1664 |
| 1.0542 | 2.0 | 186 | 0.1003 |
| 0.1156 | 3.0 | 279 | 0.0844 |
| 0.0917 | 4.0 | 372 | 0.0803 |
| 0.0776 | 5.0 | 465 | 0.0811 |
| 0.0668 | 6.0 | 558 | 0.0822 |
| 0.0592 | 7.0 | 651 | 0.0834 |
| 0.0529 | 8.0 | 744 | 0.0845 |
| 0.0482 | 9.0 | 837 | 0.0858 |
| 0.0451 | 10.0 | 930 | 0.0868 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 0
Model tree for dylanewbie/whisper-large-v2-ft-cv16-1__car50-all-format_copy2x_voiceless-241204-v1
Base model
openai/whisper-large-v2