Downloads · 30 days
10
4% of all-time downloads
cdli-whisper-lg-sulaimank-decoder-a40-5e-5-polynomial
KasuleTrevor/cdli-whisper-lg-sulaimank-decoder-a40-5e-5-polynomial
cdli-whisper-lg-sulaimank-decoder-a40-5e-5-polynomial is a automatic speech recognition model from KasuleTrevor. 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
239
Public
Parameters
242M
11 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 61%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- May 8, 2026
- Updated
- May 8, 2026
- SHA
- f572b68d
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. -->
cdli-whisper-lg-sulaimank-decoder-a40-5e-5-polynomial
This model is a fine-tuned version of sulaimank/whisper-small-luganda-400hrs on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2707
- Wer: 0.6701
- Cer: 0.3993
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: 5e-05
- train_batch_size: 8
- 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: polynomial
- lr_scheduler_warmup_steps: 300
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.3639 | 0.6784 | 500 | 1.5276 | 0.7000 | 0.4139 |
| 1.0537 | 1.3569 | 1000 | 1.3568 | 0.6768 | 0.4016 |
| 0.9755 | 2.0353 | 1500 | 1.3054 | 0.6754 | 0.4010 |
| 1.1049 | 2.7137 | 2000 | 1.2845 | 0.6732 | 0.3984 |
| 0.9403 | 3.3921 | 2500 | 1.2777 | 0.6747 | 0.3990 |
| 1.0213 | 4.0706 | 3000 | 1.2733 | 0.6728 | 0.3976 |
| 1.0177 | 4.7490 | 3500 | 1.2721 | 0.6696 | 0.3972 |
| 0.9417 | 5.4274 | 4000 | 1.2703 | 0.6683 | 0.3959 |
| 0.9993 | 6.1058 | 4500 | 1.2707 | 0.6717 | 0.3996 |
| 0.9101 | 6.7843 | 5000 | 1.2707 | 0.6701 | 0.3993 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- May 8, 2026
- Updated
- May 8, 2026