CoolFace
Modelpublic

Qulabarzi21/whisper-small-ckb-fleurs-pro

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face
0likes12downloads
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 CKB - Pro (Best Step)

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

  • —Loss: 0.3767

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: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 16
  • —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 5000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.26722.59075000.3034
0.04165.181310000.2682
0.01527.772015000.2846
0.003210.362720000.3132
0.001312.953425000.3376
0.000615.544030000.3526
0.000318.134735000.3617
0.000220.725440000.3688
0.000123.316145000.3746
0.000225.906750000.3767

Framework versions

  • —Transformers 4.57.3
  • —Pytorch 2.9.0+cu126
  • —Datasets 2.19.0
  • —Tokenizers 0.22.1