CoolFace
Modelpublic

MelanieKoe/w2v2-base-pretrained_lr5e-5_at0.8_da0.8

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes5downloads
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. -->

w2v2-base-pretrainedlr5e-5at0.8_da0.8

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 2.2369
  • —Wer: 0.1717

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: 5e-05
  • —trainbatchsize: 32
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 1000
  • —training_steps: 4000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
18.82836.762504.18241.0
3.342913.515003.24781.0
3.100420.277503.12821.0
1.859327.0310001.10740.4259
0.242833.7812501.21760.2166
0.127940.5415001.60770.1931
0.089347.317501.76470.1867
0.066954.0520001.98170.1815
0.052760.8122502.06520.1803
0.045867.5725002.12880.1850
0.040874.3227501.98090.1786
0.034581.0830002.06930.1833
0.03187.8432502.36490.1798
0.027794.5935002.32390.1721
0.0279101.3537502.17690.1730
0.0263108.1140002.23690.1717

Framework versions

  • —Transformers 4.35.0
  • —Pytorch 2.0.0
  • —Datasets 2.14.6
  • —Tokenizers 0.14.1