mo-nguyen-tmo/phowhisper_vimd

Pho Whisper Base - ViMD

This model is a fine-tuned version of vinai/PhoWhisper-base on the ViMD dataset. It achieves the following results on the evaluation set:

• Loss: 0.3062
• Wer: 19.3867

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: 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2943	1.0650	1000	0.3295	20.7727
0.2157	2.1299	2000	0.3062	19.3097
0.1877	3.1949	3000	0.3052	19.4259
0.1673	4.2599	4000	0.3062	19.3867

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.0
• Tokenizers 0.21.0