<!-- 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. -->
bengaliAI-whisper-medium-finetuned-0-50000
This model is a fine-tuned version of Rounak28/bengaliAI-whisper-medium-finetuned-0-50000 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2728
- Wer: 100.0
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: 8.000000000000001e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 50
- training_steps: 900
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4922 | 1.0 | 300 | 0.2527 | 100.0 |
| 0.9014 | 1.0 | 600 | 0.2895 | 100.0 |
| 0.4534 | 1.0 | 900 | 0.2728 | 100.0 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
