CoolFace
Modelpublic

gary109/ai-light-dance_singing_ft_wav2vec2-large-lv60-v2

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
1likes66downloads
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. -->

ai-light-dancesingingft_wav2vec2-large-lv60-v2

This model is a fine-tuned version of gary109/ai-light-dance_singing_ft_wav2vec2-large-lv60 on the ../AILIGHTDANCE.PY - ONSET-SINGING dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.4285
  • —Wer: 0.1858

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: 3e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 10.0
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.27751.011060.43720.2117
0.21542.022120.44740.2044
0.20233.033180.43720.1920
0.1864.044240.42850.1858
0.18565.055300.45890.1826
0.15376.066360.46580.1774
0.13377.077420.47690.1744
0.1088.088480.46040.1724
0.15939.099540.47310.1694
0.090410.0110600.48430.1683

Framework versions

  • —Transformers 4.20.0.dev0
  • —Pytorch 1.11.0+cu102
  • —Datasets 2.2.2.dev0
  • —Tokenizers 0.12.1