Downloads · 30 days
2
8% of all-time downloads
whisper-small-bible-splt
Leonel-Maia/whisper-small-bible-splt
whisper-small-bible-splt is a automatic speech recognition model from Leonel-Maia. 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
25
Public
Parameters
242M
10.6 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
- May 8, 2025
- Updated
- May 10, 2025
- SHA
- 9cd61e61
Base models
Datasets
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-bible-splt
This model is a fine-tuned version of openai/whisper-small on the Leonel-Maia/ewe_dataset_splitted dataset. It achieves the following results on the evaluation set:
- Loss: 0.2267
- Wer: 0.2095
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: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use 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: 500
- num_epochs: 60.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3942 | 0.6033 | 500 | 0.3759 | 0.3573 |
| 0.2466 | 1.2075 | 1000 | 0.2798 | 0.2675 |
| 0.245 | 1.8109 | 1500 | 0.2472 | 0.2347 |
| 0.2 | 2.4151 | 2000 | 0.2358 | 0.2308 |
| 0.167 | 3.0193 | 2500 | 0.2292 | 0.2115 |
| 0.1541 | 3.6226 | 3000 | 0.2267 | 0.2095 |
| 0.1292 | 4.2268 | 3500 | 0.2319 | 0.2073 |
| 0.1247 | 4.8302 | 4000 | 0.2295 | 0.2097 |
| 0.0974 | 5.4344 | 4500 | 0.2396 | 0.2109 |
| 0.0707 | 6.0386 | 5000 | 0.2479 | 0.2072 |
| 0.0774 | 6.6419 | 5500 | 0.2554 | 0.2080 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.7.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- May 8, 2025
- Updated
- May 10, 2025