All Projects → syntithenai → opensnips

syntithenai / opensnips

Licence: other
Open source projects related to Snips https://snips.ai/.

Programming Languages

javascript
184084 projects - #8 most used programming language
typescript
32286 projects
HTML
75241 projects
python
139335 projects - #7 most used programming language
coffeescript
4710 projects
shell
77523 projects

Projects that are alternatives of or similar to opensnips

Pykaldi
A Python wrapper for Kaldi
Stars: ✭ 756 (+1412%)
Mutual labels:  speech, kaldi, asr
spokestack-android
Extensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!
Stars: ✭ 52 (+4%)
Mutual labels:  nlu, speech, asr
Pytorch Asr
ASR with PyTorch
Stars: ✭ 124 (+148%)
Mutual labels:  speech, kaldi, asr
Delta
DELTA is a deep learning based natural language and speech processing platform.
Stars: ✭ 1,479 (+2858%)
Mutual labels:  nlu, speech, asr
Pytorch Kaldi
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Stars: ✭ 2,097 (+4094%)
Mutual labels:  speech, kaldi, asr
kaldi-long-audio-alignment
Long audio alignment using Kaldi
Stars: ✭ 21 (-58%)
Mutual labels:  kaldi, asr, speechrecognition
react-native-spokestack
Spokestack: give your React Native app a voice interface!
Stars: ✭ 53 (+6%)
Mutual labels:  nlu, asr
rasa-docker-arm
Rasa Docker image for ARMv7. Runs on a Raspberry Pi.
Stars: ✭ 19 (-62%)
Mutual labels:  nlu, rasa
mdmTerminal2
Голосовой терминал для MajorDoMo
Stars: ✭ 24 (-52%)
Mutual labels:  snowboy, porcupine
hermes-audio-server
An open source implementation of the audio server part of the Hermes protocol
Stars: ✭ 23 (-54%)
Mutual labels:  audio-server, snips
rasa bot example
This is an example rasa chatbot implementation that can be connected to your Facebook page.
Stars: ✭ 14 (-72%)
Mutual labels:  nlu, rasa
kaldi ag training
Docker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-grammar.
Stars: ✭ 14 (-72%)
Mutual labels:  speech, kaldi
rustfst
Rust re-implementation of OpenFST - library for constructing, combining, optimizing, and searching weighted finite-state transducers (FSTs). A Python binding is also available.
Stars: ✭ 104 (+108%)
Mutual labels:  kaldi, asr
app rasa chat bot
a stateless chat bot to perform natural language queries against the App Store top charts
Stars: ✭ 20 (-60%)
Mutual labels:  nlu, rasa
rasa-chatbot
Sample chatbot with rasa stack
Stars: ✭ 29 (-42%)
Mutual labels:  nlu, rasa
opensource-voice-tools
A repo listing known open source voice tools, ordered by where they sit in the voice stack
Stars: ✭ 21 (-58%)
Mutual labels:  speech, asr
ASR-Audio-Data-Links
A list of publically available audio data that anyone can download for ASR or other speech activities
Stars: ✭ 179 (+258%)
Mutual labels:  speech, asr
spokestack-tray-android
A UI component that makes it easy to add voice interaction to your app.
Stars: ✭ 13 (-74%)
Mutual labels:  nlu, asr
torchain
WIP: pytorch FFI wrapper for Kaldi chain loss (a.k.a. Lattice Free MMI)
Stars: ✭ 20 (-60%)
Mutual labels:  kaldi, asr
rasa milktea chatbot
Chatbot with bert chinese model, base on rasa framework(中文聊天机器人,结合bert意图分析,基于rasa框架)
Stars: ✭ 97 (+94%)
Mutual labels:  nlu, rasa

OpenSnips

This repository is DEPRECATED.

For a working full featured voice dialog manager suite see https://github.com/syntithenai/hermod

Overview

This project is home to a number of open source projects related to the Snips voice platform.

  • Hermod, a BSD-2 licenced full voice stack with a dialog manager optimised for a multi user (web hosted) environment.

  • snips-react-satellite - React component to add a microphone button to a web page that streams mqtt audio to Snips. Implements hotword,audioserver,tts and skill-server components of the Snips mqtt hermes protocol.

  • collection of assistants including meekahome music player

  • docker images for snips, nodejs, mosquitto

  • docker-compose suite to run example

Quickstart

Install docker

curl -fsSL https://get.docker.com -o get-docker.sh
$ sudo sh get-docker.sh
apt-get install docker-compose

Run the example

git clone https://github.com/syntithenai/opensnips.git
docker-compose up &

Open http://localhost:3000/ in your browser to see the microphone demo.

The opensnips repository includes a snips assistant for meekahome that supports the example AppServer intents.

"what is the time"
"what is the date"
"search for <search_topic>"

Web Browser Audioserver

More info

PulseAudio

If you are developing on Linux it is useful to have multiple access to the sound card by using pulse audio.

The docker compose file shows a container can use pulseaudio on the Linux host.

To enable

  • Run paprefs and enable network server.
  • Possibly also update volume mount in docker-compose.yml to point at cookie file (if not anon access) and PULSE_HOST to Linux IP address.

The snips image is built with alsa and pulse config compatible with the environment variables from the docker-compose file. - a custom alsa config file sets sink and source as pulseaudio - a custom pulse client config file uses settings to disable auto start of the pulse server on the client (because this setup talks directly to the host pulse server)

!! If you have a (playstation eye) microphone plugged into a always on usb power port, it may not reset on reboot and end up jammed. Switch usb ports (and reboot) to fix.

Pulseaudio Links

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].