<!-- 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. -->
dgx2_whisper_base_teacher_student_distill_att_loss_libri360_epochs_50_batch_8
This model is a fine-tuned version of rohitp1/subh_whisper_base_teacher_student_distill_att_loss_libri360_epochs_100_batch_4_ckpt1500 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1009
- Wer: 7.2700
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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5913 | 0.98 | 100 | 0.6243 | 6.3702 |
| 0.6028 | 1.97 | 200 | 0.6798 | 6.6119 |
| 0.6546 | 2.95 | 300 | 0.7314 | 6.9170 |
| 0.7386 | 3.94 | 400 | 1.3793 | 7.0099 |
| 1.2318 | 4.92 | 500 | 0.9823 | 7.0099 |
| 1.2304 | 5.91 | 600 | 1.1009 | 7.2700 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2
