metadata
library_name: transformers
language:
- multilingual
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- multilingual
metrics:
- wer
model-index:
- name: Whisper-Small-Multilingual-Uganda
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Bateesa/popolivoice, Bateesa/buaiir_voice_jap
type: multilingual
args: 'languages: japadhola, english; splits: train, test'
metrics:
- name: Wer
type: wer
value: 39.842067480258436
Whisper-Small-Multilingual-Uganda
This model is a fine-tuned version of openai/whisper-small on the Bateesa/popolivoice, Bateesa/buaiir_voice_jap dataset. It achieves the following results on the evaluation set:
- Loss: 0.7142
- Wer: 39.8421
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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Use 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0373 | 11.4943 | 1000 | 0.6213 | 29.6482 |
| 0.0125 | 22.9885 | 2000 | 0.6981 | 37.2577 |
| 0.0008 | 34.4828 | 3000 | 0.6874 | 39.6267 |
| 0.0007 | 45.9770 | 4000 | 0.7142 | 39.8421 |
Framework versions
- Transformers 5.8.0
- Pytorch 2.11.0+cu130
- Datasets 2.21.0
- Tokenizers 0.22.2