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: 0.1460
- Wer: 4.9428
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 |
|---|---|---|---|---|
| 0.4482 | 0.38 | 30 | 0.2117 | 7.6578 |
| 0.1832 | 0.75 | 60 | 0.1544 | 6.4124 |
| 0.1302 | 1.12 | 90 | 0.1546 | 6.0953 |
| 0.0785 | 1.5 | 120 | 0.1436 | 6.8765 |
| 0.0777 | 1.88 | 150 | 0.1350 | 5.3914 |
| 0.0546 | 2.25 | 180 | 0.1431 | 5.4069 |
| 0.0311 | 2.62 | 210 | 0.1411 | 9.5452 |
| 0.0334 | 3.0 | 240 | 0.1389 | 6.0334 |
| 0.0172 | 3.38 | 270 | 0.1404 | 5.1361 |
| 0.0147 | 3.75 | 300 | 0.1414 | 5.2754 |
| 0.0108 | 4.12 | 330 | 0.1420 | 5.0588 |
| 0.0073 | 4.5 | 360 | 0.1454 | 4.9273 |
| 0.007 | 4.88 | 390 | 0.1460 | 4.9428 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0