CoolFace
Modelpublic

IoanaLivia/whisper-small-finetuned-400-standard-A-epochs-10

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes2downloads
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-small-finetuned-400-standard-A-epochs-10

This model is a fine-tuned version of openai/whisper-small on the horoscopestandarda40019205_03 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5064
  • —Wer: 27.4148

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: 8
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
No log000.689041.0325
0.17221.0500.491230.1563
0.03652.01000.482528.5678
0.01343.01500.495827.7479
0.00654.02000.504628.3500
0.00425.02500.502627.6326
0.00276.03000.501827.5045
0.00197.03500.503527.4789
0.00178.04000.504827.3123
0.00159.04500.506027.4276
0.001510.05000.506427.4148

Framework versions

  • —Transformers 4.49.0
  • —Pytorch 2.5.1+cu121
  • —Datasets 3.4.0
  • —Tokenizers 0.21.0