search

harvard-edge / multilingual_kws

Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus
155 stars 35 forks source link

First time user #3

Closed El-Yazid closed 2 years ago

El-Yazid commented 3 years ago

Hello, i've read the article concerning the script, it seems great! But i'm facing problems using it for the first time, what are the files to make the embedding model ? how can i input the keywords to search for? any help would be welcomed

mmaz commented 3 years ago

Thanks - this code is still in a prerelease state unfortunately, but by July or August the repository will be organized and documented, and a pretrained embedding model will be released.

rutsam commented 2 years ago

Hello,

I wanted to know the plan to release the documentation still on course or it will be delayed

mmaz commented 2 years ago

Hi @rutsam we're still working on releasing our documentation and an end-to-end colab example, but there's a pretrained embedding model available as a prerelease in this repo, and an inference script + docker file which works with a finetuned model (see #4) produced by transfer_learning.transfer_learn.

mmaz commented 2 years ago

Our introductory Colab tutorial is now available!