octava/whisper-medium-indonesian-disaster

Whisper Medium Indonesian for Disaster Response

This model is a fine-tuned version of openai/whisper-medium on the Indonesian Speech Dataset (InaVoCript, Fleurs, OpenSLR Javanese) dataset. It achieves the following results on the evaluation set:

• Loss: 0.2632
• Wer: 9.9675

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: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1029	1.8692	1000	0.2180	11.2987
0.0165	3.7383	2000	0.2327	10.0649
0.0035	5.6075	3000	0.2444	10.3571
0.0008	7.4766	4000	0.2615	9.8377
0.0006	9.3458	5000	0.2632	9.9675

Framework versions

• Transformers 4.45.0
• Pytorch 2.8.0+cu128
• Datasets 3.0.1
• Tokenizers 0.20.0