Downloads · 30 days
7
13% of all-time downloads
finetuning-whisper-tiny-swahili-ablation_ndizi_FLEURS
smutuvi/finetuning-whisper-tiny-swahili-ablation_ndizi_FLEURS
finetuning-whisper-tiny-swahili-ablation_ndizi_FLEURS is a automatic speech recognition model from smutuvi. 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
54
Public
Parameters
37.8M
604 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 96%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025
- SHA
- 02a092e9
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. -->
finetuning-whisper-tiny-swahili-ablation_ndizi_FLEURS
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9345
- Wer: 62.6873
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: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9595 | 2.1369 | 1000 | 1.0229 | 63.6378 |
| 0.7551 | 4.2738 | 2000 | 0.9519 | 65.8682 |
| 0.6531 | 6.4107 | 3000 | 0.9368 | 62.6145 |
| 0.6085 | 8.5476 | 4000 | 0.9345 | 62.6873 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025