Downloads · 30 days
2
13% of all-time downloads
whisper-tiny-Uspeak
manasbasit/whisper-tiny-Uspeak
whisper-tiny-Uspeak is a automatic speech recognition model from manasbasit. 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
15
Public
Parameters
37.8M
604 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
- May 6, 2025
- Updated
- May 6, 2025
- SHA
- 8db37de4
Base models
Datasets
Spaces
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-Uspeak
This model is a fine-tuned version of openai/whisper-tiny on the FLEURS dataset. It achieves the following results on the evaluation set:
- Loss: 0.7984
- Wer: 22.5837
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 12
- 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
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0014 | 24.384 | 1000 | 0.6886 | 21.1693 |
| 0.0005 | 48.768 | 2000 | 0.7512 | 22.0179 |
| 0.0003 | 73.168 | 3000 | 0.7851 | 22.2065 |
| 0.0002 | 97.552 | 4000 | 0.7984 | 22.5837 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu124
- Datasets 3.5.1
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- May 6, 2025
- Updated
- May 6, 2025