luyotw/whisper-tiny-ivod-20250305-124754

Fine-tuned Whisper model for Legislative Yuan of Taiwan

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

• Loss: 0.4357
• Wer: 129.3758

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
0.1862	7.1429	1000	0.3088	142.6052
0.0974	14.2857	2000	0.3523	131.7503
0.0548	21.4286	3000	0.3969	124.3555
0.0303	28.5714	4000	0.4247	130.7327
0.0235	35.7143	5000	0.4357	129.3758

Framework versions

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