Downloads · 30 days
4
22% of all-time downloads
whisper-small-coraa-2
lejonck/whisper-small-coraa-2
whisper-small-coraa-2 is a automatic speech recognition model from lejonck. 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
18
Public
Parameters
242M
967 MB 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
- Aug 25, 2025
- Updated
- Aug 25, 2025
- SHA
- 46b94b66
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-coraa-2
This model is a fine-tuned version of lejonck/whisper-small-coraa-l.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7976
- Wer: 0.3398
- Cer: 0.5531
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: 8
- eval_batch_size: 2
- 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
- lr_scheduler_warmup_steps: 100
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.7565 | 1.0 | 750 | 0.7834 | 0.3398 | 0.5522 |
| 0.3618 | 2.0 | 1500 | 0.8102 | 0.3532 | 0.5547 |
| 0.1276 | 3.0 | 2250 | 0.8880 | 0.3562 | 0.5572 |
| 0.0482 | 4.0 | 3000 | 0.9385 | 0.3496 | 0.5567 |
| 0.0159 | 5.0 | 3750 | 0.9646 | 0.3460 | 0.5539 |
| 0.0095 | 6.0 | 4500 | 0.9888 | 0.3402 | 0.5558 |
| 0.0041 | 7.0 | 5250 | 1.0368 | 0.3406 | 0.5562 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.7.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Aug 25, 2025
- Updated
- Aug 25, 2025