Downloads · 30 days
5
36% of all-time downloads
whisper-lora-642
Jeff13680/whisper-lora-642
whisper-lora-642 is a machine learning model from Jeff13680. 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
14
Public
Repo size
111 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.8 MB · 89%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 18, 2025
- Updated
- Jul 18, 2025
- SHA
- f2469336
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-lora-642
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0266
- Wer: 0.3409
- Cer: 0.1210
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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: 50
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.4184 | 0.5674 | 10 | 1.0391 | 0.3636 | 0.1290 |
| 1.308 | 1.1135 | 20 | 1.0367 | 0.3409 | 0.1210 |
| 1.375 | 1.6809 | 30 | 1.0398 | 0.2727 | 0.0968 |
| 1.3359 | 2.2270 | 40 | 1.0344 | 0.3636 | 0.1290 |
| 1.352 | 2.7943 | 50 | 1.0320 | 0.3409 | 0.1210 |
| 1.366 | 3.3404 | 60 | 1.0297 | 0.3636 | 0.1290 |
| 1.3701 | 3.9078 | 70 | 1.0250 | 0.2727 | 0.0968 |
| 1.2679 | 4.4539 | 80 | 1.0266 | 0.3409 | 0.1210 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.2
- Pytorch 2.7.1+cu118
- Datasets 3.1.0
- Tokenizers 0.21.2
- Library
- peft
- License
- apache-2.0
- Created
- Jul 18, 2025
- Updated
- Jul 18, 2025