Downloads · 30 days
10
23% of all-time downloads
whisper-small-hre5.1
ntviet/whisper-small-hre5.1
whisper-small-hre5.1 is a automatic speech recognition model from ntviet. 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
44
Public
Parameters
242M
967 MB on disk
Likes
0
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
- Feb 21, 2025
- Updated
- Feb 22, 2025
- SHA
- 11660db7
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 Small Hre 5.1, ASR for male & female Hre voice, 1000 steps, metric CER
This model is a fine-tuned version of openai/whisper-small on the Hre audio dataset 7 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0437
- Cer Ortho: 1.6227
- Cer: 0.8702
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: 16
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer Ortho | Cer |
|---|---|---|---|---|---|
| 0.1106 | 3.2362 | 1000 | 0.0437 | 1.6227 | 0.8702 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- hre
- Created
- Feb 21, 2025
- Updated
- Feb 22, 2025