Downloads · 30 days
15
68% of all-time downloads
whisper-small-En_LoRA_R8
hagurePeco/whisper-small-En_LoRA_R8
whisper-small-En_LoRA_R8 is a machine learning model from hagurePeco. 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
22
Public
Repo size
507 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.3 MB · 98%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Nov 9, 2025
- Updated
- Nov 12, 2025
- SHA
- c658bf81
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-En_LoRA_R8
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: 2.1246
- Wer: 18.2529
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: 0.0002
- train_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 10
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.0461 | 0.1887 | 10 | 4.2767 | 26.4233 |
| 3.2927 | 0.3774 | 20 | 3.0287 | 23.5115 |
| 2.6825 | 0.5660 | 30 | 2.4277 | 21.0343 |
| 2.2553 | 0.7547 | 40 | 2.2055 | 21.3385 |
| 1.9202 | 0.9434 | 50 | 2.0987 | 19.0352 |
| 1.9872 | 1.1321 | 60 | 2.0548 | 18.8179 |
| 1.9614 | 1.3208 | 70 | 2.0168 | 18.2529 |
| 1.9076 | 1.5094 | 80 | 1.9988 | 18.0356 |
| 2.001 | 1.6981 | 90 | 2.0747 | 18.1226 |
| 2.004 | 1.8868 | 100 | 2.1246 | 18.2529 |
Framework versions
- PEFT 0.17.1
- Transformers 5.0.0.dev0
- Pytorch 2.8.0+cu126
- Datasets 2.16.0
- Tokenizers 0.22.1
- Library
- peft
- License
- apache-2.0
- Created
- Nov 9, 2025
- Updated
- Nov 12, 2025