CoolFace
Modelpublic

nrshoudi/Whisper-small-L2Arctic

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
1likes7downloads
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-L2Arctic

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

  • —Loss: 0.6319

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: 0.001
  • —trainbatchsize: 6
  • —evalbatchsize: 6
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 50
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.53211.04500.5247
0.43212.09000.5136
0.36593.013500.4786
0.3134.018000.4708
0.24685.022500.4729
0.1896.027000.5010
0.12237.031500.5433
0.07298.036000.5775
0.03639.040500.6103
0.018210.045000.6319

Framework versions

  • —PEFT 0.8.0
  • —Transformers 4.40.0
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.19.0
  • —Tokenizers 0.19.1