whisper-id-jv-multilingual-fp16-small

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1187
• Wer: 20.9952

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
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4013	0.2568	500	0.4013	75.5297
0.2703	0.5136	1000	0.2723	32.3274
0.1955	0.7704	1500	0.2118	31.1396
0.0966	1.0272	2000	0.1749	28.5714
0.0828	1.2840	2500	0.1566	23.2905
0.0788	1.5408	3000	0.1370	23.1541
0.0695	1.7976	3500	0.1250	24.0289
0.0361	2.0544	4000	0.1187	20.9952

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1