synesthesiam/voice2json

Issues

• Roadmap

  #44 opened 4 years ago by synesthesiam
  1

• voice2json-2.1 build fails at make, from curl: requested URL returned error: 404 Not Found

  #54 opened 3 years ago by OSS542
  4

• .

  #89 opened a year ago by NonaSuomy
  0

• [question] Webassembly

  #86 opened 2 years ago by jarodium
  0

• [help] transcribe-stream and transcribe-wav behaving different and giving different output

  #87 opened 2 years ago by tusharkeshav
  2

• Any possibilty to intergrate other Indic Langauages?

  #84 opened 2 years ago by solancer
  1

• Could not find a version that satisfies the requirement rhasspynlu (from versions: none)

  #83 opened 2 years ago by gnusupport
  1

• error when installing from source

  #85 opened 2 years ago by pfps
  6

• Output contains "doors"

  #82 opened 2 years ago by LukaHarambasic
  1

• libffi.so.6 no such file or directory

  #66 opened 3 years ago by sonsaeng
  3

• Pre-compiled packages do not install on Debian 11

  #63 opened 3 years ago by hendursaga
  4

• Transcribe Stream for Python script

  #81 opened 2 years ago by benimran0
  1

• GLIBC_2.28 needed

  #80 opened 2 years ago by hbarnard
  0

• no intent and slot value with the demo

  #79 opened 2 years ago by LeoMax-Xiong
  1

• using Centos 8 and tired to setup voice2json. pls help

  #77 opened 2 years ago by helpinghandindia1
  5

• Possibility of improving Chinese speech recognition (speech to text)

  #76 opened 2 years ago by SwimmingTiger
  1

• gvj

  #75 opened 2 years ago by louiskbh
  0

• Can't install on Fedora 35

  #73 opened 2 years ago by murpholinox
  1

• slow performance in raspberry

  #74 opened 3 years ago by ch-rigu
  0

• voice2json project gone quiet ? any project forum discussion available anymore ?

  #68 opened 3 years ago by OSS542
  5

• Cannot compile voice2json anymore because of ATLAS, can MKL be used for Kaldi instead?

  #70 opened 3 years ago by marcello-pietrobon
  1

• Can't build due to ATLAS

  #40 opened 4 years ago by skrat
  5

• Can't open temp files

  #71 opened 3 years ago by beto-aveiga
  3

• voice2json 2.1.deb installs files at /

  #72 opened 3 years ago by drzraf
  0

• Combined profiles to avoid having to switch between languages

  #69 opened 3 years ago by yorrd
  0

• Dockerfile broken or wrong usage ?

  #67 opened 3 years ago by CvH
  0

• Kaldi is being located inconsistently between train-profile and transcribe-wav

  #65 opened 3 years ago by mrwerdo
  0

• Using wake-word and transcribe intent at same time

  #64 opened 3 years ago by ramainen
  3

• Static/Distortion on output when server has been running a while?

  #62 opened 3 years ago by welovechatter
  0

• Question: configure voice detection delay/debounce for `transcribe-stream`?

  #61 opened 3 years ago by hiinaspace
  0

• v2.1 - transcribe-wav appears to be fairly slow

  #59 opened 3 years ago by OSS542
  1

• v2.1 - profile.defaults.yml: configure voice2json to use PulseAudio ?

  #60 opened 3 years ago by OSS542
  0

• need build procedure for voice2json to use already installed packages and python modules

  #51 opened 3 years ago by OSS542
  1

• Question: state of the art of DeepSpeech 0.9.3

  #58 opened 3 years ago by marcello-pietrobon
  0

• in scripts/build/build-phonetisaurus.sh, "build/lib" should be created if not already present

  #50 opened 3 years ago by OSS542
  2

• V2.1: no profile alias exists for en-us_pocketsphinx-cmu, required for us-en_pocketsphinx-cmu profile download

  #57 opened 3 years ago by OSS542
  0

• kenlm - reason for patched eigen headers ?

  #53 opened 3 years ago by OSS542
  1

• eigen-3.2.8 is very old, newer releases exist

  #52 opened 3 years ago by OSS542
  1

• V2.1: error in en-us_pocketsphinx-cmu profile download

  #56 opened 3 years ago by OSS542
  1

• v2.1: profile download error: FileNotFoundError: [Errno 2] No such file or directory: '/usr/share/voice2json/etc/profiles/en-us_kaldi-zamia.yml'

  #55 opened 3 years ago by OSS542
  0

• "--disable-virtualenv" switch ignored

  #49 opened 3 years ago by OSS542
  2

• [offtopic] Hackernews front page

  #42 opened 3 years ago by RidaAyed
  1

• transcribe_wav - json with timings - subtitles

  #43 opened 3 years ago by marcello-pietrobon
  1

• Vosk support

  #47 opened 3 years ago by OSS542
  2

• Docker image missing espeak-ng

  #48 opened 3 years ago by theguybieber
  0

• unable to proceed: voice2json build requires ATLAS, ATLAS does not build and is abandoned

  #46 opened 3 years ago by OSS542
  0

• getting 404's when trying to download Spanish profiles

  #45 opened 4 years ago by Sondeluz
  2

• This is a super cool project!

  #39 opened 4 years ago
  2

• crash docker illegal instruction docker (can't run deepSpeech) armv7

  #38 opened 4 years ago by charmed12
  1

• Number sequence slot not working

  #37 opened 4 years ago by djschwab
  2