Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-tms-0418-good-30_base-on-car350-250504-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: 7.8673
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 |
|---|---|---|---|
| 12.8848 | 1.0 | 1 | 13.3228 |
| 12.8451 | 2.0 | 2 | 13.3228 |
| 12.9658 | 3.0 | 3 | 13.3228 |
| 12.8821 | 4.0 | 4 | 13.3228 |
| 12.7804 | 5.0 | 5 | 13.3228 |
| 12.857 | 6.0 | 6 | 12.4657 |
| 12.046 | 7.0 | 7 | 10.7954 |
| 10.1789 | 8.0 | 8 | 10.7954 |
| 10.1851 | 9.0 | 9 | 9.1693 |
| 8.4416 | 10.0 | 10 | 7.8673 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 2.21.0
- Tokenizers 0.20.0
- Downloads last month
- 21
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for dylanewbie/whisper-large-v2-ft-tms-0418-good-30_base-on-car350-250504-v1
Base model
openai/whisper-large-v2