Downloads · 30 days
8
22% of all-time downloads
whisper-naijavoices-cvval
Abdullah804/whisper-naijavoices-cvval
whisper-naijavoices-cvval is a automatic speech recognition model from Abdullah804. 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
36
Public
Parameters
37.8M
4.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors302 MB · 98%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 26, 2025
- Updated
- Sep 7, 2025
- SHA
- b4064862
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-naijavoices-cvval
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: 6.4763
- Wer: 0.9997
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- 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
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.6619 | 0.1 | 500 | 6.3008 | 1.0 |
| 3.0567 | 0.2 | 1000 | 6.0435 | 0.9997 |
| 2.8766 | 0.3 | 1500 | 6.0737 | 0.9997 |
| 2.7863 | 0.4 | 2000 | 6.2387 | 1.0110 |
| 2.6874 | 0.5 | 2500 | 6.1798 | 1.0003 |
| 2.6776 | 0.6 | 3000 | 6.2140 | 1.0022 |
| 2.6298 | 0.7 | 3500 | 6.3933 | 1.0 |
| 2.6004 | 0.8 | 4000 | 6.4229 | 0.9984 |
| 2.5984 | 0.9 | 4500 | 6.4666 | 0.9997 |
| 2.5394 | 1.0 | 5000 | 6.4763 | 0.9997 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Aug 26, 2025
- Updated
- Sep 7, 2025