Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-my_dataset_car30_owner12_notmix_copy8x_mp3-241114-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: 0.0662
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 |
|---|---|---|---|
| 9.7151 | 1.0 | 12 | 6.0085 |
| 4.179 | 2.0 | 24 | 3.3177 |
| 2.9191 | 3.0 | 36 | 2.6056 |
| 2.2998 | 4.0 | 48 | 2.0630 |
| 1.8465 | 5.0 | 60 | 1.6640 |
| 1.4782 | 6.0 | 72 | 1.2956 |
| 1.0873 | 7.0 | 84 | 0.8528 |
| 0.6064 | 8.0 | 96 | 0.3291 |
| 0.1419 | 9.0 | 108 | 0.0435 |
| 0.0413 | 10.0 | 120 | 0.0662 |
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
- 8
Model tree for dylanewbie/whisper-large-v2-ft-my_dataset_car30_owner12_notmix_copy8x_mp3-241114-v1
Base model
openai/whisper-large-v2