ASR-cv-corpus-ug-22

This model is a fine-tuned version of piyazon/ASR-cv-corpus-ug-16 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0293
• Wer: 0.0323

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: 3e-05
• train_batch_size: 128
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 300
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0216	2.2447	4000	0.0274	0.0355
0.0123	4.4893	8000	0.0287	0.0322
0.0111	6.7340	12000	0.0293	0.0323

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu128
• Datasets 4.1.1
• Tokenizers 0.22.1