Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-cv16-1_3.5k_copy2x_half-mixed-250312-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: 0.2213
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- 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 |
|---|---|---|---|
| 3.9618 | 1.0 | 110 | 1.8612 |
| 1.0609 | 2.0 | 220 | 0.1991 |
| 0.1962 | 3.0 | 330 | 0.1863 |
| 0.1514 | 4.0 | 440 | 0.1906 |
| 0.1223 | 5.0 | 550 | 0.1943 |
| 0.1008 | 6.0 | 660 | 0.2005 |
| 0.0835 | 7.0 | 770 | 0.2058 |
| 0.0703 | 8.0 | 880 | 0.2126 |
| 0.0618 | 9.0 | 990 | 0.2185 |
| 0.0553 | 10.0 | 1100 | 0.2213 |
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
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for dylanewbie/whisper-large-v2-ft-cv16-1_3.5k_copy2x_half-mixed-250312-v1
Base model
openai/whisper-large-v2