Whisper Large-v3 Hu_v2 - snoopyben27
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1284
- Wer: 14.0572
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: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 250
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1306 | 0.0825 | 250 | 0.1284 | 14.0572 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for benmajor27/whisper-large-hu
Base model
openai/whisper-large-v3Dataset used to train benmajor27/whisper-large-hu
Evaluation results
- Wer on Common Voice 17.0test set self-reported14.057