huybunn/EraX-WoW-Turbo-V1.0-fine-tune-vi

EraX-WoW-Turbo-V1.0 Vietnamese - Huy Bunn

This model is a fine-tuned version of erax-ai/EraX-WoW-Turbo-V1.0 on the Infore1 25 hours dataset. It achieves the following results on the evaluation set:

• Loss: 0.0787
• Wer Ortho: 4.2461
• Wer: 4.1672

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0686	1.3373	250	0.0787	4.2461	4.1672

Framework versions

• Transformers 4.50.1
• Pytorch 2.6.0+cpu
• Datasets 3.4.1
• Tokenizers 0.21.1