Curiousfox/whisper_new_ver2

Hokkien-to-Tai Lo Whisper ver 2

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6832
• Wer: 137.9365

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-06
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 1000
• training_steps: 8000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.7216	0.2581	800	1.5008	134.0105
1.1329	0.5161	1600	1.0312	125.0399
0.9625	0.7742	2400	0.8906	127.3682
0.8124	1.0323	3200	0.7961	132.3214
0.7005	1.2903	4000	0.7438	127.8703
0.6735	1.5484	4800	0.7058	132.8920
0.632	1.8065	5600	0.6832	137.9365

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0