Downloads · 30 days
2
4% of all-time downloads
whisper-base-n-demo-1h
wandererupak/whisper-base-n-demo-1h
whisper-base-n-demo-1h is a automatic speech recognition model from wandererupak. 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
46
Public
Parameters
72.6M
6.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors581 MB · 50%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jan 18, 2026
- Updated
- Jan 18, 2026
- SHA
- 73f53db5
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 Base N - Fine-Tuned
This model is a fine-tuned version of openai/whisper-base on the N Demo dataset. It achieves the following results on the evaluation set:
- Loss: 0.6109
- Wer: 65.7609
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 40
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0121 | 1.8679 | 50 | 0.9410 | 91.8478 |
| 0.5803 | 3.7170 | 100 | 0.7022 | 77.7174 |
| 0.3846 | 5.5660 | 150 | 0.6276 | 75.3623 |
| 0.2721 | 7.4151 | 200 | 0.6036 | 71.1957 |
| 0.1901 | 9.2642 | 250 | 0.5887 | 67.5725 |
| 0.141 | 11.1132 | 300 | 0.5954 | 68.2971 |
| 0.1176 | 12.9811 | 350 | 0.6061 | 66.6667 |
| 0.1073 | 14.8302 | 400 | 0.6109 | 65.7609 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.9.0+cu126
- Datasets 4.5.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ne
- Created
- Jan 18, 2026
- Updated
- Jan 18, 2026