Downloads · 30 days
6
19% of all-time downloads
whisper-nonnat-5h-random-seed42
greenw0lf/whisper-nonnat-5h-random-seed42
whisper-nonnat-5h-random-seed42 is a machine learning model from greenw0lf. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
32
Public
Repo size
63 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors63 MB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- May 21, 2026
- Updated
- May 21, 2026
- SHA
- 69580b88
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
whisper-nonnat-5h-random-seed42
This model is a fine-tuned version of openai/whisper-large-v2 on the JASMIN-CGN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5234
- Wer: 17.3138
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: 0.0001
- train_batch_size: 48
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 9
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0367 | 0.1562 | 5 | 1.3379 | 44.5679 |
| 1.0623 | 0.3125 | 10 | 1.2425 | 42.5331 |
| 1.0704 | 0.4688 | 15 | 1.1041 | 39.5184 |
| 0.82 | 0.625 | 20 | 0.9672 | 37.1663 |
| 0.659 | 0.7812 | 25 | 0.8441 | 34.6276 |
| 0.8578 | 0.9375 | 30 | 0.7462 | 32.0422 |
| 0.6217 | 1.0938 | 35 | 0.6845 | 25.1913 |
| 0.5831 | 1.25 | 40 | 0.6440 | 20.8326 |
| 0.5763 | 1.4062 | 45 | 0.6127 | 20.1979 |
| 0.5348 | 1.5625 | 50 | 0.5864 | 19.4325 |
| 0.5748 | 1.7188 | 55 | 0.5673 | 19.3392 |
| 0.4604 | 1.875 | 60 | 0.5550 | 19.8339 |
| 0.442 | 2.0312 | 65 | 0.5461 | 19.8059 |
| 0.4569 | 2.1875 | 70 | 0.5388 | 19.5072 |
| 0.5058 | 2.3438 | 75 | 0.5327 | 17.5285 |
| 0.4047 | 2.5 | 80 | 0.5284 | 17.5285 |
| 0.3814 | 2.6562 | 85 | 0.5256 | 17.3978 |
| 0.5661 | 2.8125 | 90 | 0.5241 | 17.3045 |
| 0.4468 | 2.9688 | 95 | 0.5234 | 17.3138 |
Framework versions
- PEFT 0.17.1
- Transformers 4.57.6
- Pytorch 2.8.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Library
- peft
- License
- apache-2.0
- Languages
- nl
- Created
- May 21, 2026
- Updated
- May 21, 2026