CoolFace
Modelpublic

Cristhian2430/whisper-large-coes-v6

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes10downloads
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 Large SEIN - COES SEIN - Version 6

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the SEIN COES dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.3004
  • —Wer: 37.6838

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: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 4000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.0001166.66675001.108339.1544
0.0333.333310001.177937.5
0.0500.015001.217437.5
0.0666.666720001.245037.3162
0.0833.333325001.267037.5
0.01000.030001.283837.5
0.01166.666735001.295537.6838
0.01333.333340001.300437.6838

Framework versions

  • —Transformers 4.48.0.dev0
  • —Pytorch 2.5.1+cu121
  • —Datasets 3.1.0
  • —Tokenizers 0.21.0