bagasshw/ASR_Results

Whisper Tiny Java

This model is a fine-tuned version of openai/whisper-tiny.en on the jv_id_asr_split dataset. It achieves the following results on the evaluation set:

• Loss: 1.4042
• Wer: 0.6677

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
3.5162	0.4110	30	2.6041	0.9534
2.1333	0.8219	60	1.7795	0.7878
1.6574	1.2329	90	1.5370	0.7173
1.4484	1.6438	120	1.4352	0.6735
1.3908	2.0548	150	1.4042	0.6677

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0