CoolFace
Modelpublic

kiriku/whisper-small-en-homophone

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes5downloads
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. -->

Homophonesfilteddataset Whisper Small en

This model is a fine-tuned version of openai/whisper-small on the Homophones in Common Voice 15.0 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2883
  • —Wer: 34.8571

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: 4000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.23570.2510000.322244.7429
0.2540.520000.301046.5
0.23830.7530000.293540.6429
0.21631.040000.288334.8571

Framework versions

  • —Transformers 4.36.0.dev0
  • —Pytorch 1.12.1+cu113
  • —Datasets 2.15.0
  • —Tokenizers 0.15.0