Downloads · 30 days
4
13% of all-time downloads
ap-5Xhk8Aop4wgAASqzIdb3EC
mdsingh2024/ap-5Xhk8Aop4wgAASqzIdb3EC
ap-5Xhk8Aop4wgAASqzIdb3EC is a automatic speech recognition model from mdsingh2024. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
32
Public
Parameters
242M
9.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Mar 13, 2025
- Updated
- Mar 14, 2025
- SHA
- 6e84e133
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. -->
ap-5Xhk8Aop4wgAASqzIdb3EC
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: 0.4537
- Model Preparation Time: 0.0096
- Wer: 0.1243
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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: 400
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer |
|---|---|---|---|---|---|
| 0.6424 | 0.9791 | 41 | 0.6370 | 0.0096 | 0.1640 |
| 0.3145 | 1.9791 | 82 | 0.3815 | 0.0096 | 0.1333 |
| 0.233 | 2.9791 | 123 | 0.3390 | 0.0096 | 0.1237 |
| 0.1432 | 3.9791 | 164 | 0.3387 | 0.0096 | 0.1204 |
| 0.083 | 4.9791 | 205 | 0.3588 | 0.0096 | 0.1232 |
| 0.0467 | 5.9791 | 246 | 0.3956 | 0.0096 | 0.1233 |
| 0.0245 | 6.9791 | 287 | 0.4313 | 0.0096 | 0.1531 |
| 0.0191 | 7.9791 | 328 | 0.4474 | 0.0096 | 0.1258 |
| 0.0191 | 8.9791 | 369 | 0.4683 | 0.0096 | 0.1277 |
| 0.0219 | 9.9791 | 410 | 0.4537 | 0.0096 | 0.1243 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Mar 13, 2025
- Updated
- Mar 14, 2025