asd_pron_w2v_reg_balanced_500_79

This model is a fine-tuned version of slplab/wav2vec2-xls-r-300m_phone-mfa_korean on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5655
• eval_mse: 0.5650
• eval_runtime: 99.5577
• eval_samples_per_second: 6.027
• eval_steps_per_second: 0.382
• epoch: 35.0
• step: 10780

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.13.0
• Pytorch 2.0.0+cu118
• Datasets 2.14.4
• Tokenizers 0.10.3