Downloads · 30 days
8
6% of all-time downloads
whisper-large-v3-singleword
WayneTK/whisper-large-v3-singleword
whisper-large-v3-singleword is a automatic speech recognition model from WayneTK. 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
132
Public
Parameters
1.5B
49.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- May 13, 2025
- Updated
- Jun 13, 2025
- SHA
- b67cc4dd
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 Large SingleWord
This model is a fine-tuned version of openai/whisper-large-v3 on the CGE-Pronounce dataset. It achieves the following results on the evaluation set:
- Loss: 0.1488
- Wer: 17.1324
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: 16
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|---|
| 0.133 | 0.9158 | 1000 | 0.1573 | 24.6908 |
| 0.0788 | 1.8315 | 2000 | 0.1483 | 18.7357 |
| 0.0282 | 2.7473 | 3000 | 0.1458 | 17.3614 |
| 0.0104 | 3.6630 | 4000 | 0.1488 | 17.1324 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- May 13, 2025
- Updated
- Jun 13, 2025