Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-cv16-1__car500-realworld-e3n4_car30-tms-n4r2_owner12-copy2x-241212-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: 0.0856
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|
| 3.4649 | 1.0 | 211 | 0.1685 |
| 0.1756 | 2.0 | 422 | 0.0891 |
| 0.0934 | 3.0 | 633 | 0.0780 |
| 0.0706 | 4.0 | 844 | 0.0748 |
| 0.0564 | 5.0 | 1055 | 0.0740 |
| 0.0457 | 6.0 | 1266 | 0.0760 |
| 0.0376 | 7.0 | 1477 | 0.0799 |
| 0.0313 | 8.0 | 1688 | 0.0817 |
| 0.0266 | 9.0 | 1899 | 0.0839 |
| 0.0234 | 10.0 | 2110 | 0.0856 |
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
- 11
Model tree for dylanewbie/whisper-large-v2-ft-cv16-1__car500-realworld-e3n4_car30-tms-n4r2_owner12-copy2x-241212-v1
Base model
openai/whisper-large-v2