p500no-2000
This model is a fine-tuned version of openai/whisper-small on the your_dataset_name dataset. It achieves the following results on the evaluation set:
- Loss: 0.4070
- Cer: 19.4337
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0001 | 15.62 | 500 | 0.3438 | 15.9588 |
| 0.0 | 31.25 | 1000 | 0.3600 | 16.8597 |
| 0.0 | 46.88 | 1500 | 0.3804 | 18.2754 |
| 0.0 | 62.5 | 2000 | 0.4070 | 19.4337 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.4.1+cu118
- Datasets 3.0.2
- Tokenizers 0.15.2
- Downloads last month
- -
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for wanglynn/p500no-2000
Base model
openai/whisper-small