textav-components
  • Introduction
  • Guidelines for this board
    • How to add a new library/Modules/components
    • Trello --> Github --> gitbook (programmatically)
    • Plan Roadmap taxonomy
    • github README template
  • Media processing
    • ffmpeg and electron - example boilerplate
    • convert video to audio [Open Source]
    • Generate list of ffmpeg supported file formats [Open Source]
    • Detect silence [Open Source]
    • Youtube Video downloader module (?) [Open Source]
    • Module: Open source STT //Gentle refactor [Open Source]
    • cc extraction // OCR of captions [Open Source]
    • Module: Video format converter [Open Source]
    • Module: Video metadata reader [Open Source]
    • Banpass filter module
    • Tesseract - OCR
  • Transcriptions - utils
    • Transcriber module
    • Sample material for testing STT services [Open Source / CC]
    • Create word accurate time codes from line accurate time-coded transcript (eg srt)
    • Language codes ISO-639-1 Code
    • Module: Timecode conversion [Open Source]
    • UI Utilities for timecode representation
    • Sanitise string for file path
  • Transcription STT Sdk
    • Web Speech API
    • Pocket Sphinx STT [Open Source]
    • IBM Watson STT [Proprietary]
    • Google Cloud Speech API [Proprietary]
    • Microsoft Bing STT [Proprietary]
    • Baidu STT SDK [Proprietary]
    • Speechmatics STT SDK [Proprietary]
    • Spoken Data STT SDKs [Proprietary]
    • Gentle (Server) STT node SDK [Open Source]
    • Temi.com/rev.com [Proprietary]
    • Latvian Kaldi [open source]
    • Mod9
    • Movi - arduino component, offline
    • deepgram
    • Mozilla deep speech
    • AWS Transcriber
  • Transcription UI
    • Transcription text editor with Draft.js Editor [Open Source]
    • Overtyper
  • Alignement
    • Alignement
    • Module: to align partially scripted speeches
  • Captions
    • Module: captions composer (with text pre-segmentation) [Open Source]
    • Module: Captions burner [Open Source]
    • Srt parser composer // Pietro [Open Source]
    • TTML Parser // Gary, Brightcove [Open Source]
  • Annotations
    • Annotation model atjson
  • Paper-editing & remixing UI
    • Front end component: video preview of JSON Edl
  • Cognitive insights
    • LIUM Speaker Diarization BBC - [Open Source]
    • Module: open source summarization module [Open Source]
    • Module: punctuation and capitalisation. [Open Source]
  • Translation SDK
    • Deep L - Translation SDK node
  • Export & remix & video editing
    • Parse EDL (plain text) to JSON [Open Source]
    • Module: Post to facebook [Open Source]
    • EDL composer from JSON EDL [Open Source]
    • Module: Post to Twitter Video [Open Source]
    • edit video EDL (JSON) - ffmpeg-remix (super fast video editing of mp4 videos) // Laurian [Open Sourc
    • EDL Json to XML FCP7 (compatible with premiere) [Open Source]
    • Popcorn Js // Mozilla/Internet Archive [Open Source]
  • unsorted
    • NWJS boilerplate
    • QCTool
    • VRecord
    • Electron travis CI automated build: OSX, Linux, Windows
Powered by GitBook
On this page
  1. Transcription STT Sdk

Movi - arduino component, offline

PreviousMod9Nextdeepgram

Last updated 6 years ago

from this article

Which shouldn't be interpreted to mean that we're not living in the golden age of speech technology. This month, Friedland helped launch MOVI, a Kickstarted speech recognizer/voice synthesizer for Arduino that operates without the use of the cloud. "It doesn't use the Internet," Friedland says. "You don't have to use the cloud to do recognition. It can work with a couple hundred sentences and it adapts." He laughs at Sony, Apple, Google, Microsoft, and other companies that send speech into the cloud for processing. "All of this is exploiting the fact that people think [voice recognition] is so hard that it has to get done in the cloud. If you have one speaker speaking into a computer, we should consider this problem solved."

Labels

STT,

https://www.wired.com/2016/04/long-form-voice-transcription/
https://www.kickstarter.com/projects/310865303/movi-a-standalone-speech-recognizer-shield-for-ard/posts/1515592
http://www.audeme.com/
https://www.amazon.com/dp/B01C9HBL90/ref=cm_sw_su_dp
Link to trello card: Movi - arduino component, offline