bagasshw/whisper-tiny-jv-full

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: 0.2094
• Wer: 16.6655

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
0.3746	0.3242	3000	0.3745	27.3677
0.2935	0.6484	6000	0.2938	22.0987
0.2443	0.9726	9000	0.2478	19.4102
0.1576	1.2967	12000	0.2228	18.2353
0.1376	1.6209	15000	0.2094	16.6655

Framework versions

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