mo-nguyen-tmo/phowhisper_od

Pho Whisper Base - OD

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: 0.5595
• Wer: 31.6647

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
0.0014	41.6667	1000	0.5003	31.9728
0.0004	83.3333	2000	0.5321	32.8071
0.0002	125.0	3000	0.5517	32.3707
0.0002	166.6667	4000	0.5595	31.6647

Framework versions

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