CoolFace
Modelpublic

tdnathmlenthusiast/speecht5_finetuned_voice_dataset_bn_v_4

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes3downloads
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. -->

speecht5finetunedvoicedatasetbnv4

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: 0.5560

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
0.630212.12122500.5979
0.589524.24245000.5645
0.565836.36367500.5638
0.549548.484810000.5609
0.554160.606112500.5443
0.543172.727315000.5522
0.532184.848517500.5406
0.532196.969720000.5515
0.5267109.090922500.5674
0.5334121.212125000.5607
0.5202133.333327500.5586
0.52145.454530000.5560

Framework versions

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