doublex
doublex
@DigitLib Did you find a solution to reduce the size of the large-model to 3GB?
For example: This model (3GB) increases to 6GB: https://huggingface.co/bofenghuang/whisper-large-v2-cv11-german This is what I have tried: ````python from multiple_datasets.hub_default_utils import convert_hf_whisper convert_hf_whisper('bofenghuang/whisper-large-v2-cv11-german', './large-de.pt') ````
@berg-dee Does it work for you after updating the version in `peerDependencies`? Or does it throw a `Babel` error?