Downloads · 30 days
8
22% of all-time downloads
multilingual-whisper-v3-unscripted
sitwala/multilingual-whisper-v3-unscripted
multilingual-whisper-v3-unscripted is a automatic speech recognition model from sitwala. 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
36
Public
Parameters
1.5B
6.2 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
- Dec 13, 2025
- Updated
- Dec 14, 2025
- SHA
- 6414a797
Base models
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. -->
multilingual-whisper-v3-unscripted
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4354
- Wer: 0.3347
- Cer: 0.1213
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.5654 | 0.25 | 500 | 0.6164 | 0.5131 | 0.1576 |
| 0.4251 | 0.5 | 1000 | 0.5055 | 0.4647 | 0.1771 |
| 0.3301 | 0.75 | 1500 | 0.4573 | 0.3172 | 0.1060 |
| 0.2748 | 1.0 | 2000 | 0.4354 | 0.3347 | 0.1213 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.4
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Dec 13, 2025
- Updated
- Dec 14, 2025