metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-qyl-withnoise
results: []
whisper-tiny-qyl-withnoise
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: 2.0152
- 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: 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 |
|---|---|---|---|---|
| 0.0003 | 500.0 | 1000 | 1.6425 | 100.0 |
| 0.0001 | 1000.0 | 2000 | 1.8920 | 100.0 |
| 0.0001 | 1500.0 | 3000 | 1.9751 | 100.0 |
| 0.0001 | 2000.0 | 4000 | 2.0152 | 100.0 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1