Downloads · 30 days
3
0% of all-time downloads
gurbani-asr-whisper
Ashish8077/gurbani-asr-whisper
gurbani-asr-whisper is a automatic speech recognition model from Ashish8077. 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
671
Public
Parameters
242M
17.4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Apr 6, 2026
- Updated
- Apr 11, 2026
- SHA
- 22373999
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. -->
gurbani-asr-whisper
This model is a fine-tuned version of Ashish8077/gurbani-asr-whisper on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0091
- Wer: 2.0622
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- 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
- training_steps: 800
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3558 | 1.0 | 800 | 0.0091 | 2.0622 |
Framework versions
- Transformers 5.6.0.dev0
- Pytorch 2.10.0+cu128
- Datasets 4.8.5.dev0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Apr 6, 2026
- Updated
- Apr 11, 2026