CoolFace
Modelpublic

masapasa/xls-r-300m-it-cv8-ds13

sourceHugging Faceapache-2.0updated 5y agoView on Hugging Face
1likes68downloads
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. -->

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMONVOICE8_0 - SV-SE dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3549
  • —Wer: 0.3827

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: 7.5e-05
  • —trainbatchsize: 32
  • —evalbatchsize: 32
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 128
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 2000
  • —num_epochs: 50.0
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
3.41295.495003.32241.0
2.932310.9810002.91281.0000
1.683916.4815000.77400.6854
1.48521.9720000.58300.5976
1.36227.4725000.48660.4905
1.275232.9630000.42400.4967
1.195738.4635000.38990.4258
1.164643.9540000.35970.4014
1.126549.4545000.35590.3829

Framework versions

  • —Transformers 4.17.0.dev0
  • —Pytorch 1.10.2+cu102
  • —Datasets 1.18.3
  • —Tokenizers 0.11.0