speecht5_finetuned_vctk

This model is a fine-tuned version of microsoft/speecht5_tts on the jspaulsen/vctk dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4473

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: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • 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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5078 3.5476 1000 0.4718
0.4843 7.0924 2000 0.4541
0.4769 10.64 3000 0.4494
0.4746 14.1849 4000 0.4473

Framework versions

  • Transformers 4.57.3
  • Pytorch 2.9.0+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.1