CoolFace
Modelpublic

Sania67/Fine_Tunning_on_CV_dataset

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes6downloads
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. -->

FineTunningonCVdataset

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the commonvoice8_0 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.7892
  • —Wer: 0.4734

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: 0.0001
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 1000
  • —num_epochs: 30
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
6.86183.2510003.07650.9989
1.68256.4920000.89320.6292
0.78139.7430000.77500.5454
0.585912.9940000.74130.5151
0.47216.2350000.75590.4952
0.40419.4860000.76770.4915
0.363722.7370000.77880.4863
0.323825.9780000.79200.4738
0.303829.2290000.78920.4734

Framework versions

  • —Transformers 4.21.0
  • —Pytorch 1.11.0+cu113
  • —Datasets 2.4.0
  • —Tokenizers 0.12.1