<!-- 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_base_finetune_teacher_babble_noise_mozilla_100_epochs_batch_16
This model is a fine-tuned version of openai/whisper-base.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1396
- Wer: 36.8568
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 4096
- 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: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8806 | 14.7 | 250 | 0.7044 | 35.3771 |
| 0.0318 | 29.41 | 500 | 0.9696 | 36.3345 |
| 0.0022 | 44.12 | 750 | 1.0607 | 36.6235 |
| 0.0011 | 58.82 | 1000 | 1.1066 | 36.8045 |
| 0.0007 | 73.53 | 1250 | 1.1306 | 36.8359 |
| 0.0006 | 88.23 | 1500 | 1.1396 | 36.8568 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2
