luyotw/openfun-ivod-whisper-medium-XieLongJie-11-36

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: 0.0384
• Wer: 84.0803

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
0.0065	3.1646	1000	0.0302	84.9498
0.0004	6.3291	2000	0.0336	84.8161
0.0001	9.4937	3000	0.0363	84.1472
0.0	12.6582	4000	0.0377	83.8796
0.0	15.8228	5000	0.0384	84.0803

Framework versions

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