CoolFace
Modelpublic

gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v2

sourceHugging Faceupdated 4y agoView on Hugging Face
1likes14downloads
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-xlsr-53-5gram-v2

This model is a fine-tuned version of gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v1 on the GARY109/AILIGHTDANCE - ONSET-SINGING dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.4313
  • —Wer: 0.1645

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: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —gradientaccumulationsteps: 16
  • —totaltrainbatch_size: 32
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 10.0
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.1481.05520.43130.1645
0.13012.011040.43650.1618
0.12373.016560.44700.1595
0.10634.022080.45930.1576
0.1285.027600.45250.1601
0.10996.033120.45930.1567
0.09697.038640.46250.1550
0.09948.044160.46720.1543
0.1259.049680.46360.1544
0.088710.055200.46010.1538

Framework versions

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