Makkoen/whisper-large-v3-cit-do005-wd0-lr3e-06-steps1400-FULL5

<!-- 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. -->

./7326

This model is a fine-tuned version of openai/whisper-large-v3 on the 7326 FULL-2024-10-24 dataset. It achieves the following results on the evaluation set:

• —Loss: 0.3906
• —Wer Ortho: 22.5859
• —Wer: 15.5145

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: 3e-06
• —trainbatchsize: 4
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 300
• —training_steps: 1400
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.45.1
• —Pytorch 1.13.1+cu117
• —Datasets 3.0.1
• —Tokenizers 0.20.0