fallback-wolfram-alpha
mimic-recording-studio
fallback-wolfram-alpha | mimic-recording-studio | |
---|---|---|
1 | 4 | |
8 | 486 | |
- | 0.2% | |
0.0 | 0.0 | |
about 2 years ago | about 1 year ago | |
Python | JavaScript | |
Apache License 2.0 | 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.
fallback-wolfram-alpha
-
Question about where the computing/data is happening/going.
If your request does not register with a skill, it will also reach back to the Mycroft server as a final try and use the Wolfram Alpha service to try to handle it. This is the default fall-back skill. (see https://github.com/MycroftAI/fallback-wolfram-alpha)
mimic-recording-studio
-
How can I create a dataset to refine Whisper AI from old videos with subtitles?
I weirdly can't find a great off-the-shelf app for this. l'd love to know if anyone finds one. Most stuff seems to be for recording data for Text To Speech (going the other way). Mimic Recording Studio looks the best. Then there's speech training recorder and TTS Dataset Creator (video). You don't have to worry about audio quality as much as they do.
-
Experts warn people not to put Amazon Echo Alexa devices in their bedrooms
If you genuinely want to help out in that way, you can create a voice for Mycroft using their Mimic recording studio software. They reckon it takes about 40-80 hours all up.
-
Mimic 3 by Mycroft
They want you to make good quality audio recordings of you speaking about 20 000 phrases. It could take 40 to 80 hours of speaking and recording, maximum 4 hours per day.
https://github.com/MycroftAI/mimic-recording-studio
https://mycroft.ai/contribute/
- How can I immortalise my dying mums voice in some sort of voice assistant?
What are some alternatives?
mycroft-mqtt-adapter - Skill for Mycroft Voice Assistant to be controlled via MQTT protocol
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
ovos-personal-backend - personal backend - self-hosted backend to manage multiple OVOS devices
annyang - :speech_balloon: Speech recognition for your site
email-skill - Check your email with Mycroft!
google-tts - Google TTS (Text-To-Speech) for node.js
TheAlgorithms - All Algorithms implemented in Python
speaker.app - Speaker.app (https://speaker.app) is an encrypted peer-to-peer (P2P) group communication platform which does not require a user account to use. Users remain anonymous on the network unless choosing to personally identify themselves.
mycroft-core - Mycroft Core, the Mycroft Artificial Intelligence platform.
mimic3 - A fast local neural text to speech engine for Mycroft
Portainer - Making Docker and Kubernetes management easy.
Appwrite - Your backend, minus the hassle.