Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-cv16-1__car200-e3n4-A50B100_car100-n4r2_car50-r2n2_owner12-copy2x-241216-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: 0.0973
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 |
|---|---|---|---|
| 3.7031 | 1.0 | 177 | 1.0670 |
| 0.2967 | 2.0 | 354 | 0.1021 |
| 0.108 | 3.0 | 531 | 0.0896 |
| 0.0844 | 4.0 | 708 | 0.0871 |
| 0.0692 | 5.0 | 885 | 0.0867 |
| 0.0567 | 6.0 | 1062 | 0.0890 |
| 0.047 | 7.0 | 1239 | 0.0914 |
| 0.0399 | 8.0 | 1416 | 0.0927 |
| 0.0342 | 9.0 | 1593 | 0.0958 |
| 0.0305 | 10.0 | 1770 | 0.0973 |
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
- 31
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for dylanewbie/whisper-large-v2-ft-cv16-1__car200-e3n4-A50B100_car100-n4r2_car50-r2n2_owner12-copy2x-241216-v1
Base model
openai/whisper-large-v2