Downloads · 30 days
4
11% of all-time downloads
whisper-lec-vids-00
oriw2/whisper-lec-vids-00
whisper-lec-vids-00 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
35
Public
Repo size
14.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.2 MB · 78%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Apr 10, 2026
- Updated
- Apr 10, 2026
- SHA
- af57880a
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-lec-vids-00
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: 0.9879
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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8019 | 0.7220 | 200 | 2.9090 |
| 1.9955 | 1.4440 | 400 | 2.1180 |
| 1.7781 | 2.1661 | 600 | 1.9178 |
| 1.5807 | 2.8881 | 800 | 1.7943 |
| 1.4110 | 3.6101 | 1000 | 1.7113 |
| 1.4176 | 4.3321 | 1200 | 1.6073 |
| 1.1577 | 5.0542 | 1400 | 1.5100 |
| 0.9791 | 5.7762 | 1600 | 1.3678 |
| 0.7057 | 6.4982 | 1800 | 1.0794 |
| 0.6797 | 7.2202 | 2000 | 1.0473 |
| 0.7828 | 7.9422 | 2200 | 1.0380 |
| 0.6652 | 8.6643 | 2400 | 1.0321 |
| 0.7056 | 9.3863 | 2600 | 1.0130 |
| 0.5871 | 10.1083 | 2800 | 1.0070 |
| 0.6223 | 10.8303 | 3000 | 1.0039 |
| 0.6756 | 11.5523 | 3200 | 0.9992 |
| 0.5837 | 12.2744 | 3400 | 0.9969 |
| 0.7474 | 12.9964 | 3600 | 0.9953 |
| 0.5621 | 13.7184 | 3800 | 0.9848 |
| 0.6312 | 14.4404 | 4000 | 0.9939 |
| 0.5796 | 15.1625 | 4200 | 0.9893 |
| 0.7609 | 15.8845 | 4400 | 0.9916 |
| 0.6172 | 16.6065 | 4600 | 0.9873 |
| 0.5333 | 17.3285 | 4800 | 0.9928 |
| 0.6150 | 18.0505 | 5000 | 0.9873 |
| 0.6115 | 18.7726 | 5200 | 0.9879 |
| 0.4781 | 19.4946 | 5400 | 0.9879 |
| 0.5605 | 20.0 | 5540 | 0.9879 |
Framework versions
- PEFT 0.18.2.dev0
- Transformers 5.5.3
- Pytorch 2.6.0+cu124
- Datasets 4.8.4
- Tokenizers 0.22.2
- Library
- peft
- License
- apache-2.0
- Created
- Apr 10, 2026
- Updated
- Apr 10, 2026