CoolFace
Modelpublic

emilios/whisper-sm-el-farsipal-e4

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
0likes9downloads
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 Farsipal and El Greco

This model is a fine-tuned version of emilios/whisper-sm-el-farsipal-e3 on the mozilla-foundation/commonvoice11_0 el dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5430
  • —Wer: 17.1898

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: 3e-06
  • —trainbatchsize: 32
  • —evalbatchsize: 16
  • —seed: 42
  • —distributed_type: multi-GPU
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 5000

Training results

Training LossEpochStepValidation LossWer
0.00159.3510000.540517.6913
0.00118.6920000.539617.5613
0.000928.0430000.562017.4963
0.00137.3840000.545417.4591
0.001546.7350000.543017.1898

Framework versions

  • —Transformers 4.26.0.dev0
  • —Pytorch 2.0.0.dev20221216+cu116
  • —Datasets 2.7.1.dev0
  • —Tokenizers 0.13.2