CoolFace
Modelpublic

mikr/whisper-large-v3-czech-cv13

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
6likes604downloads
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. -->

openai/whisper-large-v3

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1283
  • —Wer: 0.0789

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: 62
  • —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
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.01382.2410000.09620.0863
0.0044.4820000.11170.0844
0.00156.7330000.11780.0807
0.00048.9740000.12190.0792
0.000211.2150000.12830.0789

Framework versions

  • —Transformers 4.36.0.dev0
  • —Pytorch 2.0.0+cu117
  • —Datasets 2.14.6
  • —Tokenizers 0.14.1