infinite-learning-station/whisper-tiny-restaurant

Whisper Tiny Restaurant

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

• Loss: 0.3001
• Wer: 10.5263

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: 8
• 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: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9239	33.3333	100	0.2999	10.5263
0.0015	66.6667	200	0.2268	10.5263
0.0005	100.0	300	0.2590	10.5263
0.0002	133.3333	400	0.2807	10.5263
0.0001	166.6667	500	0.3001	10.5263

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.4.2
• Tokenizers 0.22.1