snowboy
Porcupine
snowboy | Porcupine | |
---|---|---|
6 | 31 | |
2,973 | 3,452 | |
1.5% | 2.0% | |
0.0 | 9.0 | |
over 2 years ago | 12 days ago | |
C++ | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
snowboy
-
How to train large deep learning models as a startup
Great question. This is technically referred to as "Wake Word Detection". You run a really small model locally that is just processing 500ms (for example) of audio at a time through a light weight CNN or RNN. The idea here is that it's just binary classification (vs actual speech recognition).
There are some open source libraries that make this relatively easy:
- https://github.com/Kitt-AI/snowboy (looks to be shutdown now)
-
Getting Rid of Dust / 1.0.0-beta.4
Leon uses Snowboy for its hotword detection. Unfortunately the project has been discontinued and is suffering from the lack of maintainability.
-
Self-Made-Robot: Review Robots Projects
Voice recognition: Snowboy Hotword Detection - closed 2020-12-31
-
Build A Raspberry Pi Amazon Echo in 7 Steps: A Tutorial
For step 6, setting up the wake word, the post recommends KITT.AI or Sensory, but Kitt is closing down and Sensory is not free. Do you know of any other services that are still around and well maintained?
-
Sunday Daily Thread: What's everyone working on this week?
Looks really nice and clean! Have you by chance tested out the snowboy hotword detector https://github.com/Kitt-AI/snowboy? (Just noticed that they are actually shutting down)
-
help executing tasks with assistant using autovoice.
hi, i just checked it and really loved the plugin, but saw that the site that used to analyze the voice to make a new hotword (https://github.com/Kitt-AI/snowboy) got shut down at 31/12/2020, and i havent find any other place that can do that :(
Porcupine
-
I made a ChatGPT virtual assistant that you can talk to
I call it DaVinci. DaVinci uses Picovoice (https://picovoice.ai/) solutions for wake word and voice activity detection and for converting speech to text, Amazon Polly to convert its responses into a natural sounding voice, and OpenAI’s GPT 3.5 to do the heavy lifting. It’s all contained in about 300 lines of Python code.
-
Speech Recognition in Unity: Adding Voice Input
Download pre-trained models: "Porcupine" from Porcupine Wake Word and Video Player Context from Rhino Speech-to-Intent repositories - You can also train a custom models on Picovoice Console.
-
Speech Recognition with SwiftUI
Below are some useful resources: Open-source code Picovoice Platform SDK Picovoice website
-
Speech Recognition with Angular
Download the Porcupine model and turn the binary model into a base64 string.
-
OK Google, Add Hotword Detection to Chrome
Download Porcupine (i.e. Deep Neural Network). Run the following to turn the binary model into a base64 string, from the project folder.
-
Hotword Detection for MCUs
Porcupine SDK Porcupine SDK is on GitHub. Find libraries for supported MCUs on the Porcupine GitHub repository. Arduino libraries are available via a specialized package manager offered by Arduino.
-
Day 12: Always Listening Voice Commands with React.js
Looking for more? Explore other languages on the Picovoice Console and check out for fully-working demos with Porcupine on GitHub.
-
Day 6: Making Cool Raspberry Pi Projects even Cooler with Voice AI (1/4)
Don't forget to visit Porcupine's Wake Word's Github repository to see Python demos. If you want to do something similar to the video above, find the open-source codes here
- Voice Assistant app in Haskell
-
What does "end-to-end" mean?
I sometimes see the term "end-to-end", and it always passes right by my ears as marketing jargon. For example, there was a recent post today that linked to this page: https://picovoice.ai/, and you'll find the statement "... end-to-end platform for adding voice to anything on your terms". I did a quick Google search and it seems like the term is used in many different contexts (e.g., encryption, enterprise software for product development, etc.), but to be honest, I'm just not getting it. Maybe someone can explain here within the realm of embedded software? Could you provide some examples as well?
What are some alternatives?
pocketsphinx - A small speech recognizer
mycroft-precise - A lightweight, simple-to-use, RNN wake word listener
BalancingWii - Self balancing robot (Segway) based on modified/extended MultiWii 2.3 firmware.
Caffe - Caffe: a fast open framework for deep learning.
Leon - 🧠 Leon is your open-source personal assistant.
DeepSpeech - DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
Express - Fast, unopinionated, minimalist web framework for node.
mxnet - Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
spokestack-python - Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application with a focus on embedded systems.
Caffe2
determined - Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.
Serpent.AI - Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!