asr_minds

This model is a fine-tuned version of w11wo/wav2vec2-xls-r-300m-korean on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.4650
• eval_wer: 4.4083
• eval_runtime: 20.5998
• eval_samples_per_second: 5.777
• eval_steps_per_second: 0.728
• epoch: 1.6667
• step: 50

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 500
• training_steps: 2000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.1+cu128
• Datasets 4.0.0
• Tokenizers 0.22.1