CoolFace
Modelpublic

shivam/xls-r-hindi

sourceHugging Faceapache-2.0updated 5y agoView on Hugging Face
1likes68downloads
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/COMMONVOICE7_0 - HI dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.4484
  • —Wer: 1.0145

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: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 32
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 2000
  • —num_epochs: 50.0
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
5.18443.45005.20150.9999
3.39626.810003.40171.0002
2.543310.215001.68841.0222
1.509913.620000.79291.0188
1.268517.0125000.61221.0191
1.184420.4130000.54341.0197
1.094523.8135000.52081.0316
1.050627.2140000.49411.0139
1.019930.6145000.47361.0106
0.954634.0150000.46641.0164
0.938837.4155000.45651.0085
0.912540.8160000.46361.0148
0.873344.2265000.45301.0154
0.882947.6270000.44941.0152

Framework versions

  • —Transformers 4.16.0.dev0
  • —Pytorch 1.10.1+cu102
  • —Datasets 1.17.1.dev0
  • —Tokenizers 0.11.0