CoolFace
Modelpublic

sil-ai/senga-nt-canon-tts

sourceHugging Facemitupdated 2mo agoView on Hugging Face
0likes9downloads
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-nt-canon-tts

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: 0.0913

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: 4000
  • —training_steps: 40000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.16439.216620000.1102
0.159718.433240000.1029
0.141727.649860000.0986
0.133336.866480000.0984
0.125446.0829100000.0962
0.124455.2995120000.0956
0.118364.5161140000.0958
0.11473.7327160000.0961
0.118982.9493180000.0949
0.107892.1659200000.0928
0.1064101.3825220000.0936
0.1029110.5991240000.0930
0.0971119.8157260000.0916
0.094129.0323280000.0912
0.0943138.2488300000.0919
0.0906147.4654320000.0920
0.0931156.6820340000.0916
0.0918165.8986360000.0915
0.089175.1152380000.0915
0.0905184.3318400000.0913

Framework versions

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