architparnami / few-shot-kws Goto Github PK

View Code? Open in Web Editor NEW

49.0 49.0 16.0 2.3 MB

Few-Shot Keyword Spotting

Python 4.53% Shell 0.25% Jupyter Notebook 95.22%

audio few-shot-recognition keyword-spotting prototypical-networks speech-recognition

few-shot-kws's Introduction

few-shot-kws's People

Contributors

Stargazers

Watchers

Forkers

elenazy rxhmdia ductho9799 adigeak saikirandingu wuyx517 wangwenxi-handsome yatindra7 r170455-ckr road2018 scott0910 liux-pro jinmingche bilalrahib flcaus romenlongcode

few-shot-kws's Issues

Licesne?

What's the license for the code? MIT? Thanks!

How can I search this paper ”Few-Shot Keyword Spotting with Prototypical Networks“

I can’t find this paper，am I search wrong word？

Dependency: Torchaudio 0.8.0 normalization -> nomalize

Basically need to change all torchaudio.load(normalization=) to torchaudio.load(normalize=)

It might be a good idea to specify the version in dependencies.

Feasibility of this research for real time deployment

Dear Author,
first of all I would like to say that this work is a very good solution for low data resource kws. Thank you for sharing the e2e training recipe of this novel idea.
I am interested to know if this is a reliable solution for real time Speech commands recognition on low power embedded devices.
Another question I would like to ask is:
Could we use the Embedding extractor model which was trained for 10-way 15-shot experiment for deploying into a 6-way keyword spotting pipeline?

Thanks,
Saikiran

Recommend Projects