v01_30_NLEM_Aug_Tablets_Model
This model is a fine-tuned version of openai/whisper-large on the /30_NLEM_Aug_audios_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Wer: 0.0
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 218
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0529 | 1.0 | 44 | 0.0042 | 0.0 |
| 0.0003 | 2.0 | 88 | 0.0001 | 0.0 |
| 0.0 | 3.0 | 132 | 0.0000 | 0.0 |
| 0.0 | 4.0 | 176 | 0.0000 | 0.0 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
- Downloads last month
- 7
Model tree for deepinfinityai/v01_Model
Base model
openai/whisper-largeDataset used to train deepinfinityai/v01_Model
Evaluation results
- Wer on /30_NLEM_Aug_audios_datasetself-reported0.000