CoolFace
Modelpublic

rishabhjain16/whisper_large_to_myst55h

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. -->

openai/whisper-large

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

  • —Loss: 0.4047
  • —Wer: 11.5273

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: 32
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 4000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.57440.125000.348814.3862
0.21431.0210000.295612.6669
0.17761.1515000.289211.5103
0.05622.0420000.325711.8171
0.1682.1725000.311512.6878
0.01783.0730000.384911.3784
0.02623.1935000.373411.3523
0.00834.0940000.404711.5273

Framework versions

  • —Transformers 4.27.0.dev0
  • —Pytorch 1.13.1+cu117
  • —Datasets 2.9.1.dev0
  • —Tokenizers 0.13.2