<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
dgx1_whisper_small_finetune_teacher_no_noise_mozilla_40_epochs_batch_8
This model is a fine-tuned version of openai/whisper-small.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5458
- Wer: 25.6772
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1812 | 14.7 | 500 | 0.5279 | 26.9793 |
| 0.002 | 29.41 | 1000 | 0.5458 | 25.6772 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2
