Downloads · 30 days
4
12% of all-time downloads
whisper-small-SIT_08_07_26_0632
horhh/whisper-small-SIT_08_07_26_0632
whisper-small-SIT_08_07_26_0632 is a automatic speech recognition model from horhh. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
34
Public
Parameters
242M
967 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- Jul 8, 2026
- Updated
- Jul 8, 2026
- SHA
- e81355b3
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-SIT_08_07_26_0632
This model is a fine-tuned version of Pengwin30/whisper-small-fine-tuned on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0079
- Wer: 0.3976
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: 4
- seed: 42
- gradient_accumulation_steps: 2
- 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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4201 | 1.0 | 361 | 0.0115 | 0.7290 |
| 0.0196 | 2.0 | 722 | 0.0087 | 0.7290 |
| 0.0034 | 3.0 | 1083 | 0.0079 | 0.3976 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 2.19.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- mit
- Created
- Jul 8, 2026
- Updated
- Jul 8, 2026