Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-cv16-1_random_mix-241031-v2
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: 0.1927
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 |
|---|---|---|---|
| 4.3848 | 1.0 | 56 | 2.3268 |
| 1.7142 | 2.0 | 112 | 0.7692 |
| 0.4967 | 3.0 | 168 | 0.1981 |
| 0.2173 | 4.0 | 224 | 0.1893 |
| 0.1942 | 5.0 | 280 | 0.1875 |
| 0.1777 | 6.0 | 336 | 0.1885 |
| 0.1649 | 7.0 | 392 | 0.1900 |
| 0.1554 | 8.0 | 448 | 0.1904 |
| 0.1478 | 9.0 | 504 | 0.1920 |
| 0.1428 | 10.0 | 560 | 0.1927 |
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
- 10
Model tree for dylanewbie/whisper-large-v2-ft-cv16-1_random_mix-241031-v2
Base model
openai/whisper-large-v2