CoolFace
Modelpublic

jcmc/wav2vec-1b-cv8-ir-n

sourceHugging Faceapache-2.0updated 5y agoView on Hugging Face
0likes38downloads
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-1b on the MOZILLA-FOUNDATION/COMMONVOICE8_0 - GA-IE dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.9810
  • —Wer: 0.4761

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: 2e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 32
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 1000
  • —num_epochs: 100.0
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
2.242715.155001.46320.9481
1.312830.310000.86620.6195
0.940345.4515000.81630.5169
0.686860.6120000.86610.4858
0.56375.7625000.94470.4867
0.488790.9130000.96500.4823

Framework versions

  • —Transformers 4.17.0.dev0
  • —Pytorch 1.10.2+cu102
  • —Datasets 1.18.2.dev0
  • —Tokenizers 0.11.0