CoolFace
Modelpublic

gary109/ai-light-dance_singing2_ft_wav2vec2-large-xlsr-53-5gram-v4-2

sourceHugging Faceupdated 4y agoView on Hugging Face
1likes20downloads
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-dancesinging2ft_wav2vec2-large-xlsr-53-5gram-v4-2

This model is a fine-tuned version of gary109/ai-light-dance_singing2_ft_wav2vec2-large-xlsr-53-5gram-v4-1 on the GARY109/AILIGHTDANCE - ONSET-SINGING2 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2691
  • —Wer: 0.0910

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: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 100
  • —num_epochs: 10.0
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.26641.089690.33470.1645
0.20322.0179380.31700.1662
0.18883.0269070.31880.1317
0.17744.0358760.28850.1195
0.06965.0448450.27030.1105
0.2546.0538140.28170.0972
0.04647.0627830.26910.0910
0.04268.0717520.30330.0875
0.0359.0807210.31500.0841
0.027410.0896900.30730.0816

Framework versions

  • —Transformers 4.21.0.dev0
  • —Pytorch 1.9.1+cu102
  • —Datasets 2.3.3.dev0
  • —Tokenizers 0.12.1