luyotw/whisper-small-ivod-20250306-105539

Fine-tuned Whisper model for Legislative Yuan of Taiwan

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

• Loss: 0.3221
• Wer: 112.5509

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
0.0452	7.1429	1000	0.2375	110.0407
0.0023	14.2857	2000	0.2882	112.3474
0.001	21.4286	3000	0.3069	115.3324
0.0006	28.5714	4000	0.3175	111.8725
0.0005	35.7143	5000	0.3221	112.5509

Framework versions

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