CoolFace
Modelpublic

khushi1234455687/wav2vec2-large-xlsr-53-Hindi-Version3

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes8downloads
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-large-xlsr-53-Hindi-Version3

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

  • —Loss: 0.7311
  • —Wer: 0.2821

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: 0.0003
  • —trainbatchsize: 16
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 32
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 100
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
3.3626.75685003.37951.0
0.530913.513510000.55720.4268
0.234220.270315000.52060.3341
0.140827.027020000.55160.3292
0.112633.783825000.61050.3199
0.089240.540530000.64890.3123
0.072147.297335000.65330.3067
0.071954.054140000.68980.3050
0.059260.810845000.70070.2990
0.073767.567650000.71060.2921
0.039974.324355000.72710.2916
0.040981.081160000.72980.2871
0.032287.837865000.73110.2835
0.028594.594670000.73110.2821

Framework versions

  • —Transformers 4.45.0.dev0
  • —Pytorch 2.4.1+cu121
  • —Datasets 2.21.0
  • —Tokenizers 0.19.1