CoolFace
Modelpublic

sethilakshay/wav2vec2-base-finetune-v2-flickr8k

sourceHugging Faceapache-2.0updated 3y 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. -->

wav2vec2-base-finetune-v2-flickr8k

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1698
  • —Wer: 0.1382

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: 12
  • —evalbatchsize: 2
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
1.79951.610000.29230.2001
0.29813.220000.22470.1525
0.21254.830000.18270.1490
0.21566.440000.20090.1445
0.27838.050000.16780.1412
0.15619.660000.16980.1382

Framework versions

  • —Transformers 4.27.4
  • —Pytorch 2.0.0
  • —Datasets 2.11.0
  • —Tokenizers 0.13.2