metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-small-bangla-english
results: []
whisper-small-bangla-english
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.9861
- Wer: 421.4861
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0134 | 27.78 | 1000 | 4.2948 | 340.9132 |
| 0.0002 | 55.56 | 2000 | 4.8454 | 429.7225 |
| 0.0001 | 83.33 | 3000 | 4.9496 | 410.4745 |
| 0.0001 | 111.11 | 4000 | 4.9861 | 421.4861 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0