Downloads · 30 days
6
5% of all-time downloads
whisper-small-lozi1
simzacademy/whisper-small-lozi1
whisper-small-lozi1 is a automatic speech recognition model from simzacademy. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
115
Public
Parameters
241M
25 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors962 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- Aug 8, 2025
- Updated
- Aug 18, 2025
- SHA
- b68052db
Base models
Spaces
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 Lozi - Lozi ASR
This model is a fine-tuned version of simzacademy/whisper-small-tonga on the csikasote/Lozi dataset. It achieves the following results on the evaluation set:
- Loss: 1.0924
- Wer: 49.4069
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: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0336 | 20.0 | 500 | 0.9876 | 50.9406 |
| 0.0006 | 40.0 | 1000 | 1.0734 | 48.9491 |
| 0.0004 | 60.0 | 1500 | 1.0924 | 49.4069 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- mit
- Created
- Aug 8, 2025
- Updated
- Aug 18, 2025