CoolFace
Modelpublic

anuragshas/wav2vec2-xls-r-300m-or-cv9-with-lm

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes50downloads
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/COMMONVOICE9_0 - OR dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.7886
  • —Wer: 0.5495
  • —Cer: 0.1311

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: 64
  • —evalbatchsize: 64
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 128
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —training_steps: 3071
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWerCer
3.587566.624003.42891.01.0
1.4065133.318000.72430.66190.1734
1.007199.9212000.66110.58310.1457
0.7984266.6216000.63870.55200.1332
0.6117333.3120000.74240.56820.1376
0.4926399.9224000.76270.55140.1314
0.416466.6228000.78160.56040.1320

Framework versions

  • —Transformers 4.19.0.dev0
  • —Pytorch 1.11.0+cu102
  • —Datasets 2.1.1.dev0
  • —Tokenizers 0.12.1