metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-id
results: []
whisper-tiny-id
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: 0.5406
- Wer: 108.0794
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: 32
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.3496 | 3.86 | 1000 | 0.4832 | 68.7427 |
| 0.1256 | 7.72 | 2000 | 0.4856 | 85.7807 |
| 0.0512 | 11.58 | 3000 | 0.5275 | 104.5165 |
| 0.0336 | 15.44 | 4000 | 0.5406 | 108.0794 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.16.1
- Tokenizers 0.15.0