metadata
library_name: transformers
language:
- su
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- whisper
- sundanese
- asr
- generated_from_trainer
datasets:
- su_id_asr_split
metrics:
- wer
model-index:
- name: Whisper Tiny Sunda
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: su_id_asr_split
type: su_id_asr_split
config: su_id_asr_source
split: validation
args: su_id_asr_source
metrics:
- name: Wer
type: wer
value: 0.5419133964515518
Whisper Tiny Sunda
This model is a fine-tuned version of openai/whisper-tiny on the su_id_asr_split dataset. It achieves the following results on the evaluation set:
- Loss: 0.4974
- Wer: 0.5419
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: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- 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: 30
- training_steps: 150
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.8761 | 0.0219 | 30 | 1.2365 | 0.7810 |
| 0.9096 | 0.0438 | 60 | 0.7216 | 0.5673 |
| 0.6491 | 0.0657 | 90 | 0.5795 | 0.5316 |
| 0.5444 | 0.0876 | 120 | 0.5178 | 0.5609 |
| 0.4887 | 0.1095 | 150 | 0.4975 | 0.5418 |
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.6.0+cu126
- Datasets 3.3.2
- Tokenizers 0.21.0