CoolFace
Modelpublic

gary109/ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v6

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes13downloads
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-dancestepmaniaft_wav2vec2-large-xlsr-53-v6

This model is a fine-tuned version of gary109/ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v5 on the GARY109/AILIGHTDANCE - ONSET-STEPMANIA2 dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.0063
  • —Wer: 0.6580

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: 4e-05
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 8
  • —totaltrainbatch_size: 64
  • —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
0.85721.03761.05080.6601
0.86712.07521.07550.6581
0.85783.011281.01520.6787
0.85524.015041.05370.6557
0.83545.018801.03860.6606
0.85436.022561.00630.6580
0.85567.026321.04870.6499
0.83568.030081.04070.6549
0.82279.033841.03820.6506
0.814810.037601.04400.6500

Framework versions

  • —Transformers 4.21.0.dev0
  • —Pytorch 1.11.0+cu113
  • —Datasets 2.3.3.dev0
  • —Tokenizers 0.12.1