Download Latest Version v2.5.11.zip (8.0 MB)
Email in envelope

Get an email when there's a new version of Rhasspy

Home / v2.5.11
Name Modified Size InfoDownloads / Week
Parent folder
rhasspy_amd64.deb 2021-09-10 261.4 MB
0
rhasspy_armhf.deb 2021-09-10 248.4 MB
0
rhasspy_arm64.deb 2021-09-10 223.0 MB
0
rhasspy_armel.deb 2021-09-10 138.5 MB
0
README.md 2021-09-10 1.3 kB
0
v2.5.11.tar.gz 2021-09-10 8.0 MB
0
v2.5.11.zip 2021-09-10 8.0 MB
1 1 weekly downloads
Totals: 7 Items   887.3 MB 1

Added

  • Option to allow "unknown" words to be recognized with Kaldi with Text FST grammar enabled
  • Changeable "cancel" word that can be spoken at any time to trigger a recognition failure
  • Preliminary support for Arabic (ar)
  • Initial support for Vosk ASR (English, German, French, Spanish, Italian, Russian, Portuguese, Vietnamese, Arabic)
  • New Larynx voices for German, Dutch, and English
  • Multiple audio streams for Precise/Porcupine/Snowboy/Pocketsphinx wake word service (thanks Romkabouter)
  • Raven speed optimizations for dynamic time warping code (thanks maxbachmann)
  • Dialogue manager will convert audio files to WAV using soundfile and audioread
  • dialogue.sound_suffixes profile setting controls file extensions searched for when dialogue feedback sound path is a directory
  • rhasspy-speakers-cli-mqtt will convert audio bytes to WAV using soundfile and audioread
  • Wake word systems can receive raw UDP audio from multiple sites, and forward it to MQTT (see wake.<system>.udp_site_info)

Fixed

  • Websocket queues are retained between restarts (thanks sabeechen)
  • Avoid skipping 0 value in fsticuffs intent recognition
  • Fix fsticuffs bug for dropping multiple words: [foo | bar]:

Changed

  • The rhasspy-silence CLI tool can now split audio by silence and trim silence
Source: README.md, updated 2021-09-10