Downloads · 30 days
4
11% of all-time downloads
whisper-40hrs-random
greenw0lf/whisper-40hrs-random
whisper-40hrs-random 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
36
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
- Sep 19, 2025
- Updated
- Sep 19, 2025
- SHA
- 2d208a0f
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-40hrs-random
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: 0.3683
- Wer: 18.1098
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: 48
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 87
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0401 | 0.1730 | 50 | 1.1988 | 37.8200 |
| 0.9555 | 0.3460 | 100 | 1.0688 | 35.7265 |
| 0.7947 | 0.5190 | 150 | 0.8653 | 33.0325 |
| 0.6554 | 0.6920 | 200 | 0.6321 | 29.0670 |
| 0.5346 | 0.8651 | 250 | 0.4921 | 21.8841 |
| 0.4683 | 1.0381 | 300 | 0.4321 | 21.6291 |
| 0.4501 | 1.2111 | 350 | 0.4115 | 21.6392 |
| 0.4317 | 1.3841 | 400 | 0.3999 | 20.9716 |
| 0.4454 | 1.5571 | 450 | 0.3916 | 20.1765 |
| 0.4168 | 1.7301 | 500 | 0.3848 | 18.5091 |
| 0.4096 | 1.9031 | 550 | 0.3802 | 18.6701 |
| 0.3981 | 2.0761 | 600 | 0.3763 | 18.2474 |
| 0.4189 | 2.2491 | 650 | 0.3732 | 18.4487 |
| 0.4301 | 2.4221 | 700 | 0.3712 | 18.1870 |
| 0.4046 | 2.5952 | 750 | 0.3697 | 18.3380 |
| 0.4244 | 2.7682 | 800 | 0.3687 | 18.0897 |
| 0.4068 | 2.9412 | 850 | 0.3683 | 18.1098 |
Framework versions
- PEFT 0.16.0
- Transformers 4.52.0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.2
- Library
- peft
- License
- apache-2.0
- Languages
- nl
- Created
- Sep 19, 2025
- Updated
- Sep 19, 2025