whisper-finetuned-nan-tw-v3-torbo

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2539

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1911	1.0616	500	0.2122
0.1615	2.1233	1000	0.2177
0.1291	3.1849	1500	0.2198
0.1014	4.2465	2000	0.2262
0.0852	5.3082	2500	0.2331
0.077	6.3698	3000	0.2422
0.07	7.4315	3500	0.2472
0.0647	8.4931	4000	0.2496
0.06	9.5547	4500	0.2539

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0