CoolFace
Modelpublic

pollitoconpapass/whisper-small-cuzco-quechua

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes1.2kdownloads
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

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

  • —Loss: 0.0002

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: 0.0001
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —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 Loss
0.076512.55000.0630
0.041325.010000.0294
0.017337.515000.0191
0.016150.020000.0116
0.007862.525000.0046
0.007175.030000.0039
0.001987.535000.0015
0.001100.040000.0002
0.0007112.545000.0002
0.0125.050000.0002

Framework versions

  • —Transformers 4.39.0
  • —Pytorch 2.3.0+cu121
  • —Datasets 2.18.0
  • —Tokenizers 0.15.2