longgb/whisper-muong-final

<!-- 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-muong-final

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

• —Loss: 0.8115
• —Wer: 74.2356

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: 4
• —evalbatchsize: 4
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 32
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 50
• —training_steps: 800
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —PEFT 0.18.0
• —Transformers 4.57.3
• —Pytorch 2.6.0+cu124
• —Datasets 4.4.1
• —Tokenizers 0.22.1