CoolFace
Modelpublic

MarioNapoli/DynamicWav2Vec_TEST_10

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes9downloads
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. -->

DynamicWav2VecTEST10

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the commonvoice1_0 dataset. It achieves the following results on the evaluation set:

  • —Loss: 2.9344
  • —Wer: 1.0

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: 0.0003
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 30

Training results

Training LossEpochStepValidation LossWer
3.57922.684002.96421.0
2.95395.358002.98821.0
2.94768.0312003.03841.0
2.949710.716002.95241.0
2.956213.3820002.93321.0
2.94516.0524002.98581.0
2.938318.7328002.94191.0
2.931121.432002.93281.0
2.929824.0836002.93751.0
2.927326.7640002.93521.0
2.92129.4344002.93441.0

Framework versions

  • —Transformers 4.32.0
  • —Pytorch 2.0.1+cu118
  • —Datasets 2.14.4
  • —Tokenizers 0.13.3