wav2vec2-finetune-authentic-and-synth

• Loss: 0.8896
• Wer: 0.3800

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 5e-06
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• 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
• num_epochs: 5

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0
• Datasets 3.5.0
• Tokenizers 0.21.0