metadata
language:
- nl
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Large V2
results: []
Whisper Large V2
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3288
- Wer: 10.1449
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: 3e-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: 20
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.547 | 0.49 | 30 | 0.3162 | 11.6867 |
| 0.2746 | 0.98 | 60 | 0.2737 | 11.8923 |
| 0.1356 | 1.48 | 90 | 0.2783 | 12.7351 |
| 0.1356 | 1.97 | 120 | 0.2870 | 12.4165 |
| 0.0697 | 2.46 | 150 | 0.2864 | 11.5223 |
| 0.0544 | 2.95 | 180 | 0.2922 | 10.3505 |
| 0.0246 | 3.44 | 210 | 0.3186 | 10.3916 |
| 0.0217 | 3.93 | 240 | 0.3104 | 10.2580 |
| 0.0113 | 4.43 | 270 | 0.3237 | 10.2066 |
| 0.009 | 4.92 | 300 | 0.3288 | 10.1449 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0