CoolFace
Modelpublic

girikabin/whisper-NEPALI-LARGE-v2-common-17

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes3downloads
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 Large v2 Hi - Kabin

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3904

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: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 50
  • —num_epochs: 3
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
1.5530.6944250.8388
0.5081.3889500.4456
0.32762.0833750.3984
0.162.77781000.3904

Framework versions

  • —PEFT 0.9.0
  • —Transformers 4.46.0.dev0
  • —Pytorch 2.4.1+cu121
  • —Datasets 3.0.1
  • —Tokenizers 0.20.1