CoolFace
Modelpublic

lorenzoncina/whisper-small-en-no-8bitoptm

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes17downloads
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 English

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/commonvoice11_0 en dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3266
  • —Wer: 13.0386

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: 32
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 10000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.15290.110000.438117.7766
0.23720.220000.398815.9201
0.17060.330000.384115.5069
0.27810.440000.369714.8122
0.21670.550000.357614.2563
0.36090.660000.404118.0670
0.24550.770000.337213.4813
0.25020.880000.339313.5810
0.25640.990000.330313.1041
0.23941.0100000.326613.0386

Framework versions

  • —Transformers 4.28.0.dev0
  • —Pytorch 2.0.0+cu117
  • —Datasets 2.11.1.dev0
  • —Tokenizers 0.13.2