Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-cv16-1__my_dataset_car50_n4r2_owner12_notmix_copy2x_mp3-241122-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: 0.1190
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 |
|---|---|---|---|
| 4.3895 | 1.0 | 61 | 2.3177 |
| 1.5003 | 2.0 | 122 | 0.1778 |
| 0.3613 | 3.0 | 183 | 0.1206 |
| 0.1301 | 4.0 | 244 | 0.1150 |
| 0.1131 | 5.0 | 305 | 0.1140 |
| 0.1 | 6.0 | 366 | 0.1142 |
| 0.0898 | 7.0 | 427 | 0.1154 |
| 0.0829 | 8.0 | 488 | 0.1174 |
| 0.0779 | 9.0 | 549 | 0.1186 |
| 0.0737 | 10.0 | 610 | 0.1190 |
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
- 2
Model tree for dylanewbie/whisper-large-v2-ft-cv16-1__my_dataset_car50_n4r2_owner12_notmix_copy2x_mp3-241122-v1
Base model
openai/whisper-large-v2