Michael Hansen

opentts. Open Text to Speech Server

voice2json. Command-line tools for speech and intent recognition on Linux

rhasspy. Rhasspy voice assistant for offline home automation

docker-mozillatts. Docker image for Mozilla TTS server

homeassistant-satellite. Streaming audio satellite for Home Assistant

magicpy. An autostereogram (MagicEye) image generator written in Python

old-custom-components. A voice assistant toolkit for Home Assistant

coqui-docker. Docker images for Coqui AI

hassio-addons. My Hass.IO add-ons

docker-marytts. MaryTTS text to speech server and a collection of voices for various languages

eyecode. Python library for analyzing gaze data from programmers

voice-recorder. Simple tkinter application for recorded voice samples with text prompts

jsgf-gen. Tool for generating tagged sentences from JSGF grammars

voice2json-profiles. Speech models and artifacts for voice2json

pt-br_pocketsphinx-cmu. Portuguese voice2json profile based on Pocketsphinx

zh-cn_pocketsphinx-cmu. Mandarin voice2json profile based on Pocketsphinx

jsgf2fst. Python

en-us_deepspeech-mozilla. U.S. English profile for Mozilla DeepSpeech

homeassistant-pipeline. Websocket client for Assist audio pipeline

de_deepspeech-aashishag. German profile using Mozilla's DeepSpeech and Aashishag Model

eyecode-tools. A collection of tools for analyzing data from my eyeCode experiment

ru_pocketsphinx-cmu. Russian voice2json profile based on Pocketsphinx

openwakeword-satellite. Basic satellite for Home Assistant running openWakeWord locally

wav-chunk. Read or write INFO chunks in WAV files

novice. Special Python image submodule for beginners

en-us_pocketsphinx-cmu. U.S. English voice2json profile based on Pocketsphinx

el-gr_pocketsphinx-cmu. Greek voice2json profile based on Pocketsphinx

en-us_kaldi-zamia. U.S. English voice2json profile based on Kaldi

de_kaldi-zamia. German voice2json profile based on Kaldi

rhasspy-profiles. Language-specific profiles for Rhasspy Hass.io add-on

mnemofy. Python utility to convert between words and mnemonic numbers

artwork. Some of my art (for some definition of art)

motion-sensor. Wakes/sleeps a Raspberry Pi display using a PIR sensor

word2phonemes. Grapheme to phoneme guesser using PyTorch

fr_kaldi-guyot. French profile for voice2json using Kaldi with Paul Guyot's TDN 250 model

pl_julius-github. Polish voice2json profile based on Julius

speech-to-text-alignment. Aligning / Biasing Speech-to-Text models to a predefined set of words or phrases.

docker-deepvoice3. DeepVoice3 web server with pre-trained English models

coqui-tts-tests. Test sound files for Coqui TTS

rhasspy-asr-kaldi. Automated speech recognition library for Rhasspy using Kaldi

esphome-nabu. C++

vi_kaldi-montreal. Vietnamese voice2json profile based on Kaldi

pt-synesthesiam. CMU Sphinx acoustic model for Portugese (pt-br)

public-domain-sounds. Compressed WAV files from Public Domain Sounds

esphome. ESPHome is a system to control your ESP8266/ESP32 by simple yet powerful configuration files and control them remotely through Home Automation systems.

marytts-txt2wav. Command-line utility for text to speech with MaryTTS

wav-decoder. Basic WAV file decoder in C++