Downloads · 30 days
3
10% of all-time downloads
whisper-nonnat-5h-random-seed333
greenw0lf/whisper-nonnat-5h-random-seed333
whisper-nonnat-5h-random-seed333 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
29
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
- 5b1cb6c8
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-seed333
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: 0.5208
- Wer: 18.3778
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: 10
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0023 | 0.1515 | 5 | 1.3400 | 44.2785 |
| 1.0472 | 0.3030 | 10 | 1.2532 | 43.4478 |
| 0.8951 | 0.4545 | 15 | 1.1128 | 40.1157 |
| 0.979 | 0.6061 | 20 | 0.9752 | 37.5770 |
| 0.8326 | 0.7576 | 25 | 0.8511 | 39.0610 |
| 0.701 | 0.9091 | 30 | 0.7512 | 34.6183 |
| 0.5083 | 1.0606 | 35 | 0.6850 | 26.2087 |
| 0.6136 | 1.2121 | 40 | 0.6448 | 21.7286 |
| 0.6453 | 1.3636 | 45 | 0.6096 | 19.1525 |
| 0.4892 | 1.5152 | 50 | 0.5818 | 18.2005 |
| 0.5009 | 1.6667 | 55 | 0.5640 | 17.8831 |
| 0.3788 | 1.8182 | 60 | 0.5514 | 17.8085 |
| 0.5336 | 1.9697 | 65 | 0.5423 | 17.5005 |
| 0.5214 | 2.1212 | 70 | 0.5354 | 17.3698 |
| 0.4278 | 2.2727 | 75 | 0.5304 | 18.4618 |
| 0.416 | 2.4242 | 80 | 0.5259 | 18.4712 |
| 0.5102 | 2.5758 | 85 | 0.5233 | 18.3872 |
| 0.4586 | 2.7273 | 90 | 0.5217 | 18.3872 |
| 0.4488 | 2.8788 | 95 | 0.5208 | 18.3778 |
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