Skip to content
This repository has been archived by the owner on Aug 30, 2020. It is now read-only.

Multiple siteIDs ignored (2.5) #239

Open
MichaelKirgus opened this issue Jun 9, 2020 · 1 comment
Open

Multiple siteIDs ignored (2.5) #239

MichaelKirgus opened this issue Jun 9, 2020 · 1 comment

Comments

@MichaelKirgus
Copy link

After upgrading to 2.5 (coming from 2.5-pre) with the docker image rhasspyserver_hermes seems not to subscribe the siteIDs for recording audio frames.
Config:

{ "dialogue": { "satellite_site_ids": "s1,s2,s3,s4,s5,s6", "system": "rhasspy" }, "intent": { "fuzzywuzzy": { "min_confidence": "0.2" }, "satellite_site_ids": "s1,s2,s3,s4,s5,s6", "system": "fuzzywuzzy" }, "microphone": { "system": "hermes" }, "mqtt": { "enabled": "true", "host": "rhasspy" }, "speech_to_text": { "satellite_site_ids": "s1,s2,s3,s4,s5,s6", "system": "pocketsphinx" }, "wake": { "pocketsphinx": { "keyphrase": "alexa" }, "porcupine": { "keyword_path": "alexa.ppn", "sensitivity": "0.5", "udp_audio": "" }, "satellite_site_ids": "s1,s2,s3,s4,s5,s6", "snowboy": { "model": "alexa.ppn" }, "system": "porcupine" } }

Log:

[DEBUG:2020-06-09 19:08:32,380] rhasspyprofile.download: speech_to_text.deepspeech.mix_weight >0 0 = False [DEBUG:2020-06-09 19:08:32,380] rhasspyprofile.download: speech_to_text.kaldi.mix_weight >0 0 = False [DEBUG:2020-06-09 19:08:32,379] rhasspyprofile.download: speech_to_text.pocketsphinx.mix_weight >0 0 = False [DEBUG:2020-06-09 19:08:32,379] rhasspyprofile.download: speech_to_text.deepspeech.open_transcription True False = False [DEBUG:2020-06-09 19:08:32,379] rhasspyprofile.download: speech_to_text.kaldi.open_transcription True False = False [DEBUG:2020-06-09 19:08:32,378] rhasspyprofile.download: speech_to_text.pocketsphinx.open_transcription True False = False [DEBUG:2020-06-09 19:08:32,378] rhasspyprofile.download: speech_to_text.system deepspeech pocketsphinx = False [DEBUG:2020-06-09 19:08:32,378] rhasspyprofile.download: speech_to_text.system kaldi pocketsphinx = False [DEBUG:2020-06-09 19:08:32,378] rhasspyprofile.download: Skipping acoustic_model/variances (/profiles/de/acoustic_model/variances) [DEBUG:2020-06-09 19:08:32,378] rhasspyprofile.download: Skipping acoustic_model/transition_matrices (/profiles/de/acoustic_model/transition_matrices) [DEBUG:2020-06-09 19:08:32,377] rhasspyprofile.download: Skipping acoustic_model/noisedict (/profiles/de/acoustic_model/noisedict) [DEBUG:2020-06-09 19:08:32,377] rhasspyprofile.download: Skipping acoustic_model/mixture_weights (/profiles/de/acoustic_model/mixture_weights) [DEBUG:2020-06-09 19:08:32,377] rhasspyprofile.download: Skipping acoustic_model/means (/profiles/de/acoustic_model/means) [DEBUG:2020-06-09 19:08:32,376] rhasspyprofile.download: Skipping acoustic_model/mdef (/profiles/de/acoustic_model/mdef) [DEBUG:2020-06-09 19:08:32,376] rhasspyprofile.download: Skipping acoustic_model/feature_transform (/profiles/de/acoustic_model/feature_transform) [DEBUG:2020-06-09 19:08:32,376] rhasspyprofile.download: Skipping acoustic_model/feat.params (/profiles/de/acoustic_model/feat.params) [DEBUG:2020-06-09 19:08:32,376] rhasspyprofile.download: Skipping g2p.fst (/profiles/de/g2p.fst) [DEBUG:2020-06-09 19:08:32,375] rhasspyprofile.download: Skipping base_dictionary.txt (/profiles/de/base_dictionary.txt) [DEBUG:2020-06-09 19:08:32,375] rhasspyprofile.download: speech_to_text.system pocketsphinx pocketsphinx = True [INFO:2020-06-09 19:08:32,302] rhasspyserver_hermes: Started [DEBUG:2020-06-09 19:08:32,302] rhasspyserver_hermes: Subscribed to hermes/hotword/+/detected [DEBUG:2020-06-09 19:08:32,301] rhasspyserver_hermes: Subscribed to hermes/nlu/intentNotRecognized [DEBUG:2020-06-09 19:08:32,301] rhasspyserver_hermes: Subscribed to hermes/asr/textCaptured [DEBUG:2020-06-09 19:08:32,301] rhasspyserver_hermes: Subscribed to rhasspy/asr/default/default/audioCaptured [DEBUG:2020-06-09 19:08:32,300] rhasspyserver_hermes: Subscribed to hermes/intent/# [DEBUG:2020-06-09 19:08:32,300] rhasspyserver_hermes: Subscribed to hermes/audioServer/default/audioSummary [DEBUG:2020-06-09 19:08:32,300] rhasspyserver_hermes: Subscribed to hermes/audioServer/default/audioSummary [DEBUG:2020-06-09 19:08:32,300] rhasspyserver_hermes: Subscribed to rhasspy/asr/default/default/audioCaptured [DEBUG:2020-06-09 19:08:32,299] rhasspyserver_hermes: Subscribed to hermes/nlu/intentNotRecognized [DEBUG:2020-06-09 19:08:32,299] rhasspyserver_hermes: Subscribed to hermes/intent/# [DEBUG:2020-06-09 19:08:32,299] rhasspyserver_hermes: Subscribed to hermes/asr/textCaptured [DEBUG:2020-06-09 19:08:32,298] rhasspyserver_hermes: Subscribed to hermes/hotword/+/detected [DEBUG:2020-06-09 19:08:32,298] rhasspyserver_hermes: Connected to MQTT broker [DEBUG:2020-06-09 19:08:32,294] rhasspyserver_hermes: Connecting to rhasspy:1883 (retries: 0/10) [DEBUG:2020-06-09 19:08:32,294] rhasspyserver_hermes: Starting core [DEBUG:2020-06-09 19:08:32,291] rhasspyprofile.profile: Loading default profile settings from /usr/lib/rhasspy/lib/python3.7/site-packages/rhasspyprofile/profiles/defaults.json [DEBUG:2020-06-09 19:08:32,291] rhasspyprofile.profile: Loading /profiles/de/profile.json [DEBUG:2020-06-09 19:08:32,290] rhasspyprofile.profile: Loading /usr/lib/rhasspy/lib/python3.7/site-packages/rhasspyprofile/profiles/de/profile.json [DEBUG:2020-06-09 19:08:32,111] rhasspyserver_hermes: Restarting Rhasspy

I want to use multiple "stupid" pi zeros with only audio-streaming to my central VM and there is no wake-word detection even if i push the "Wake" button on the Web-GUI on my VM...

@synesthesiam
Copy link
Owner

rhasspy-server-hermes doesn't usually subscribe to audio frames. You need to set the "Satellite site IDs" in the settings page for your ASR (speech to text) and NLU (text to intent) systems.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants