metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-bn
results: []
language:
- bn
pipeline_tag: automatic-speech-recognition
whisper-tiny-bn
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4041
- Wer: 100.9994
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.5443 | 4.67 | 500 | 1.0344 | 180.0125 |
| 0.3201 | 9.35 | 1000 | 0.2322 | 121.4866 |
| 0.0545 | 14.02 | 1500 | 0.2617 | 128.8570 |
| 0.0116 | 18.69 | 2000 | 0.3251 | 95.9400 |
| 0.0031 | 23.36 | 2500 | 0.3768 | 101.7489 |
| 0.0007 | 28.04 | 3000 | 0.3905 | 98.5634 |
| 0.0004 | 32.71 | 3500 | 0.4006 | 101.1868 |
| 0.0003 | 37.38 | 4000 | 0.4041 | 100.9994 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3