luyotw/whisper-medium-ivod-20250313-093608

Fine-tuned Whisper model for Legislative Yuan of Taiwan

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

• Loss: 0.0248
• Wer: 64.9979

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0129	1.3812	1000	0.0191	64.9028
0.008	2.7624	2000	0.0203	66.6984
0.0015	4.1436	3000	0.0230	65.4098
0.0008	5.5249	4000	0.0241	64.8500
0.0002	6.9061	5000	0.0248	64.9979

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1
• Datasets 2.19.1
• Tokenizers 0.20.1