Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-cv16-1_mix-241027-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: 3.4671
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 |
|---|---|---|---|
| 6.5689 | 1.0 | 1 | 7.5824 |
| 6.532 | 2.0 | 2 | 6.9088 |
| 6.0432 | 3.0 | 3 | 5.6531 |
| 4.8988 | 4.0 | 4 | 4.6871 |
| 4.2119 | 5.0 | 5 | 4.1478 |
| 3.6408 | 6.0 | 6 | 3.8492 |
| 3.5934 | 7.0 | 7 | 3.6741 |
| 3.3356 | 8.0 | 8 | 3.5618 |
| 3.1882 | 9.0 | 9 | 3.4971 |
| 3.1682 | 10.0 | 10 | 3.4671 |
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
- 4
Model tree for dylanewbie/whisper-large-v2-ft-cv16-1_mix-241027-v1
Base model
openai/whisper-large-v2