CoolFace
Modelpublic

sil-ai/senga-LUK-20k-clean-speecht5

sourceHugging Facemitupdated 3mo agoView on Hugging Face
0likes7downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

senga-LUK-20k-clean-speecht5

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1049

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: 0.0001
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 3407
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 32
  • —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 2000
  • —training_steps: 20000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.093390.909110000.0817
0.076181.818220000.0809
0.0629272.727330000.0836
0.0599363.636440000.0844
0.0559454.545550000.0894
0.0511545.454560000.0913
0.0478636.363670000.0950
0.0436727.272780000.0971
0.045818.181890000.0973
0.0407909.0909100000.1029
0.03951000.0110000.1021
0.04091090.9091120000.1015
0.03721181.8182130000.1045
0.0381272.7273140000.1031
0.03561363.6364150000.1075
0.03691454.5455160000.1048
0.03621545.4545170000.1046
0.04211636.3636180000.1072
0.03641727.2727190000.1068
0.03811818.1818200000.1049

Framework versions

  • —Transformers 4.57.1
  • —Pytorch 2.8.0+cu128
  • —Datasets 4.2.0
  • —Tokenizers 0.22.2