metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-atcosim
results: []
whisper-tiny-atcosim
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0719
- Wer: 71.6707
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.214 | 8.33 | 500 | 0.0634 | 15.5816 |
| 0.0022 | 16.67 | 1000 | 0.0635 | 33.2191 |
| 0.0008 | 25.0 | 1500 | 0.0656 | 41.1928 |
| 0.0003 | 33.33 | 2000 | 0.0668 | 52.5468 |
| 0.0002 | 41.67 | 2500 | 0.0679 | 59.4184 |
| 0.0002 | 50.0 | 3000 | 0.0688 | 64.3591 |
| 0.0001 | 58.33 | 3500 | 0.0696 | 65.6742 |
| 0.0001 | 66.67 | 4000 | 0.0703 | 68.3969 |
| 0.0001 | 75.0 | 4500 | 0.0710 | 69.3740 |
| 0.0001 | 83.33 | 5000 | 0.0714 | 70.2260 |
| 0.0001 | 91.67 | 5500 | 0.0718 | 71.5966 |
| 0.0001 | 100.0 | 6000 | 0.0719 | 71.6707 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.0