Downloads · 30 days
9
36% of all-time downloads
whisper-tiny-ScienceTechnology-V3
wwwtwwwt/whisper-tiny-ScienceTechnology-V3
whisper-tiny-ScienceTechnology-V3 is a automatic speech recognition model from wwwtwwwt. 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
37.8M
151 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Apr 3, 2025
- Updated
- Apr 3, 2025
- SHA
- be10a0d8
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-tiny-ScienceTechnology-V3
This model is a fine-tuned version of wwwtwwwt/whisper-tiny-no-specific-topic-V3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5691
- Wer: 29.6114
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 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
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7516 | 1.018 | 500 | 0.5488 | 33.6209 |
| 0.5703 | 2.036 | 1000 | 0.5228 | 29.2281 |
| 0.2939 | 3.054 | 1500 | 0.5216 | 27.5269 |
| 0.1171 | 4.072 | 2000 | 0.5501 | 27.7425 |
| 0.1032 | 5.09 | 2500 | 0.5823 | 30.6497 |
| 0.1129 | 6.108 | 3000 | 0.5691 | 29.6114 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.5.1+cu121
- Datasets 3.5.0
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Apr 3, 2025
- Updated
- Apr 3, 2025