Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
On-device wake word detection powered by deep learning
- wake-word-detection
- hotword
- keyword-spotting
- keyword-spotter
Saves up to 90% of AWS EC2 costs by automating the use of spot instances on existing AutoScaling groups. Installs in minutes using CloudFormation or Terraform. Convenient to deploy at scale using StackSets. Uses tagging to avoid launch configuration changes. Automated spot termination handling. Reliable fallback to on-demand instances.
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
Keyword spotting on Arm Cortex-M Microcontrollers
A lightweight, simple-to-use, RNN wake word listener
- wake-word-detection
- keyword-spotting
- hotword-detection
- voice-recognition
Deep learning for audio processing
Production First and Production Ready End-to-End Keyword Spotting Toolkit
Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)
- ttnet
- pytorch
- tabletennis
- sport-analytics
:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection
TextBoxes: A Fast Text Detector with a Single Deep Neural Network
- aaai
- scene
- text
- detection
Lightweight on-device keyword spotting engine for iOS using CoreML and real-time audio streaming.