Downloads · 30 days
8
6% of all-time downloads
whisper-small-test-essays
oriw2/whisper-small-test-essays
whisper-small-test-essays is a machine learning model from oriw2. 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
129
Public
Repo size
199 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt56.9 MB · 51%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Mar 11, 2026
- Updated
- Mar 17, 2026
- SHA
- 8e573dbc
Base models
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-small-test-essays
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4338
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 34
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5551 | 0.625 | 10 | 2.9387 |
| 2.6607 | 1.25 | 20 | 2.8341 |
| 2.1610 | 1.875 | 30 | 2.7483 |
| 2.1276 | 2.5 | 40 | 2.6714 |
| 2.0351 | 3.125 | 50 | 2.6076 |
| 2.0774 | 3.75 | 60 | 2.5457 |
| 1.7293 | 4.375 | 70 | 2.4908 |
| 1.9631 | 5.0 | 80 | 2.4361 |
| 1.7491 | 5.625 | 90 | 2.3838 |
| 1.8006 | 6.25 | 100 | 2.3310 |
| 1.8468 | 6.875 | 110 | 2.2762 |
| 1.8833 | 7.5 | 120 | 2.2200 |
| 1.5741 | 8.125 | 130 | 2.1610 |
| 1.5473 | 8.75 | 140 | 2.1028 |
| 1.5371 | 9.375 | 150 | 2.0426 |
| 1.3498 | 10.0 | 160 | 1.9806 |
| 1.3618 | 10.625 | 170 | 1.9171 |
| 1.2757 | 11.25 | 180 | 1.8585 |
| 1.2838 | 11.875 | 190 | 1.8027 |
| 1.1870 | 12.5 | 200 | 1.7550 |
| 1.1328 | 13.125 | 210 | 1.7099 |
| 1.0353 | 13.75 | 220 | 1.6720 |
| 1.1403 | 14.375 | 230 | 1.6480 |
| 1.0024 | 15.0 | 240 | 1.6283 |
| 1.0437 | 15.625 | 250 | 1.6079 |
| 1.0980 | 16.25 | 260 | 1.5981 |
| 1.0157 | 16.875 | 270 | 1.5854 |
| 1.0230 | 17.5 | 280 | 1.5721 |
| 1.0170 | 18.125 | 290 | 1.5609 |
| 0.9733 | 18.75 | 300 | 1.5536 |
| 0.9620 | 19.375 | 310 | 1.5424 |
| 0.9989 | 20.0 | 320 | 1.5344 |
| 0.9384 | 20.625 | 330 | 1.5244 |
| 0.9582 | 21.25 | 340 | 1.5158 |
| 0.9295 | 21.875 | 350 | 1.5088 |
| 0.9364 | 22.5 | 360 | 1.5024 |
| 0.8725 | 23.125 | 370 | 1.4920 |
| 0.9017 | 23.75 | 380 | 1.4866 |
| 0.8884 | 24.375 | 390 | 1.4823 |
| 0.8317 | 25.0 | 400 | 1.4760 |
| 0.8735 | 25.625 | 410 | 1.4696 |
| 0.9376 | 26.25 | 420 | 1.4631 |
| 0.8584 | 26.875 | 430 | 1.4604 |
| 0.8888 | 27.5 | 440 | 1.4555 |
| 0.8238 | 28.125 | 450 | 1.4507 |
| 0.8615 | 28.75 | 460 | 1.4464 |
| 0.7650 | 29.375 | 470 | 1.4434 |
| 0.8829 | 30.0 | 480 | 1.4399 |
| 0.7883 | 30.625 | 490 | 1.4387 |
| 0.9044 | 31.25 | 500 | 1.4352 |
| 0.7897 | 31.875 | 510 | 1.4335 |
| 0.7674 | 32.5 | 520 | 1.4341 |
| 1.0575 | 33.125 | 530 | 1.4319 |
| 0.7941 | 33.75 | 540 | 1.4338 |
Framework versions
- PEFT 0.18.2.dev0
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.2
- Tokenizers 0.22.2
- Library
- peft
- License
- apache-2.0
- Created
- Mar 11, 2026
- Updated
- Mar 17, 2026