<!-- 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_libri360_noisy_teacher_interleaved_dataset_distil_epochs_50_batch_4_try2
This model is a fine-tuned version of rohitp1/dgx2_whisper_small_finetune_teacher_babble_noise_libri_360_hours_50_epochs_batch_8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8330
- Wer: 8.9519
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 1024
- 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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0247 | 0.74 | 150 | 0.0998 | 8.9666 |
| 0.0927 | 1.48 | 300 | 0.1621 | 8.8958 |
| 0.1626 | 2.22 | 450 | 0.2224 | 8.9059 |
| 0.2571 | 2.95 | 600 | 0.3091 | 8.9059 |
| 0.4578 | 3.69 | 750 | 0.4165 | 8.9225 |
| 0.5417 | 4.43 | 900 | 0.5238 | 8.9519 |
| 0.7906 | 5.17 | 1050 | 0.8330 | 8.9519 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2
