CoolFace
Modelpublic

Aakali/whisper-medium-hi-translate-jee

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes3downloads
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. -->

Whisper medium-translate Hi - Aa

This model is a fine-tuned version of Aakali/whisper-medium-hi on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • —Loss: 2.4968
  • —Wer: 23.6842

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: 1e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 5000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.01000.010001.218213.1579
0.02000.020001.736018.4211
0.03000.030002.148423.6842
0.04000.040002.510626.3158
0.05000.050002.496823.6842

Framework versions

  • —Transformers 4.41.0
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1