CoolFace
Modelpublic

tdnathmlenthusiast/speecht5_finetuned_voice_dataset_bn_v_3

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes8downloads
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. -->

speecht5finetunedvoicedatasetbnv3

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

  • —Loss: 0.5008

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
  • —trainbatchsize: 4
  • —evalbatchsize: 2
  • —seed: 42
  • —gradientaccumulationsteps: 8
  • —totaltrainbatch_size: 32
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 125
  • —training_steps: 3000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.604612.26992500.5646
0.558324.53995000.5268
0.536436.80987500.5188
0.517149.079810000.5087
0.509861.349712500.5018
0.50173.619615000.5022
0.498485.889617500.4955
0.492998.159520000.5000
0.4933110.429422500.4944
0.4868122.699425000.5006
0.4805134.969327500.4991
0.4802147.239330000.5008

Framework versions

  • —Transformers 4.44.2
  • —Pytorch 2.4.1+cu121
  • —Datasets 3.0.1
  • —Tokenizers 0.19.1