Downloads · 30 days
7
39% of all-time downloads
whisper-hf-adalora-phi-elimination
SPL123/whisper-hf-adalora-phi-elimination
whisper-hf-adalora-phi-elimination is a machine learning model from SPL123. 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 mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
18
Public
Repo size
839 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.9 MB · 63%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 12, 2025
- Updated
- Aug 18, 2025
- SHA
- ba8df475
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-hf-adalora-phi-elimination
This model is a fine-tuned version of openai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4551
- Wer: 0.2287
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
- gradient_accumulation_steps: 4
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 500
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.9698 | 1.0 | 92 | 1.8133 | 0.2323 |
| 2.0076 | 2.0 | 184 | 1.8015 | 0.2325 |
| 1.9317 | 3.0 | 276 | 1.7803 | 0.2325 |
| 1.9494 | 4.0 | 368 | 1.7484 | 0.2317 |
| 1.9152 | 5.0 | 460 | 1.7007 | 0.2294 |
| 1.8371 | 6.0 | 552 | 1.6332 | 0.2291 |
| 1.8062 | 7.0 | 644 | 1.5497 | 0.2279 |
| 1.7041 | 8.0 | 736 | 1.4551 | 0.2287 |
Framework versions
- PEFT 0.17.0
- Transformers 4.55.1
- Pytorch 2.6.0+cu124
- Datasets 2.18.0
- Tokenizers 0.21.4
- Library
- peft
- License
- mit
- Created
- Aug 12, 2025
- Updated
- Aug 18, 2025