Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-cv16-1__my_dataset_car50_owner12_notmix_copy8x_mp3-241114-test
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: 3.9773
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 |
|---|---|---|---|
| 9.189 | 1.0 | 1 | 8.9039 |
| 8.996 | 2.0 | 2 | 8.1058 |
| 8.0375 | 3.0 | 3 | 6.7183 |
| 6.5938 | 4.0 | 4 | 5.6775 |
| 5.6671 | 5.0 | 5 | 4.8798 |
| 4.9006 | 6.0 | 6 | 4.4965 |
| 4.5562 | 7.0 | 7 | 4.2646 |
| 4.2602 | 8.0 | 8 | 4.1061 |
| 4.1225 | 9.0 | 9 | 4.0191 |
| 4.0125 | 10.0 | 10 | 3.9773 |
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
- 5
Model tree for dylanewbie/whisper-large-v2-ft-cv16-1__my_dataset_car50_owner12_notmix_copy8x_mp3-241114-test
Base model
openai/whisper-large-v2