search

vasistalodagala / whisper-finetune

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.
MIT License
262 stars 57 forks source link

Insufficient VRAM #19

Open J-Korn opened 3 months ago

J-Korn commented 3 months ago

While trying to finetune the openai/whisper-medium model with the google/fleurs dataset, even only using one language (greek) I very soon run out of VRAM, on a 20GB VRAM GPU.

Is there some way to reduce the VRAM consumption?

gongouveia commented 1 week ago

@J-Korn Please use a lower batch size