bagasshw/whisper-tiny-jv-filtered

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

• Loss: 0.1864
• Wer: 15.5907

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: 3.75e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• 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: 15000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.357	0.3685	3000	0.3480	25.8908
0.2706	0.7370	6000	0.2641	21.1006
0.1495	1.1055	9000	0.2240	18.1716
0.1449	1.4740	12000	0.2000	16.6219
0.1255	1.8425	15000	0.1864	15.5907

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.7.0+cu128
• Datasets 2.18.0
• Tokenizers 0.21.1