Speech-To-Text Transcription Issue

Help
1

Hello!

I’m facing some problem with Transcription part in speech recognition. When ever I hit wake up button or use hot word to capture my command/speech it’s not transcribing. However, I confirmed that speech is recorded by playing last recorded wav file.It does capture my voice but somehow not able to translate it and thus not able to recognize intent.

Setup overview:

Rapsberry Pi 3B+ running Raspbian Buster
Rhasspy 2.5.9 on Docker
intent: fsticuffs
speech_to_text: kaldi
text_to_speech: nanotts
hotword: porcupine

One more thing I want to mention, If I write sentence and hit recognize magically it works but when I use hotword or wake up it does not work as stated above.

Kindly see log file for more clarification:
1. when I try to give voice command

 rhasspyserver_hermes: Publishing 44 bytes(s) to hermes/asr/toggleOn
 rhasspyserver_hermes: -> AsrToggleOn(site_id='default', reason=<AsrToggleReason.PLAY_AUDIO: 'playAudio'>)
 rhasspyserver_hermes: Publishing 44 bytes(s) to hermes/hotword/toggleOn
 rhasspyserver_hermes: -> HotwordToggleOn(site_id='default', reason=<HotwordToggleReason.PLAY_AUDIO: 'playAudio'>)
 rhasspyserver_hermes: Handling AudioPlayFinished (topic=hermes/audioServer/default/playFinished, id=6a62736f-1eea-4ffb-aa3c-3a8ef298925b)
 rhasspyserver_hermes: Handling AudioPlayBytes (topic=hermes/audioServer/default/playBytes/a1d3ae2a-c0f3-4d53-b4fd-b10af397b735, id=80e2cac5-ea21-422d-89ea-8ce8209a3626)
 rhasspyserver_hermes: -> AudioPlayBytes(52844 byte(s))
 rhasspyserver_hermes: Publishing 44 bytes(s) to hermes/asr/toggleOff
 rhasspyserver_hermes: -> AsrToggleOff(site_id='default', reason=<AsrToggleReason.PLAY_AUDIO: 'playAudio'>)
 rhasspyserver_hermes: Publishing 44 bytes(s) to hermes/hotword/toggleOff
 rhasspyserver_hermes: -> HotwordToggleOff(site_id='default', reason=<HotwordToggleReason.PLAY_AUDIO: 'playAudio'>)
 rhasspyserver_hermes: Playing 52844 byte(s)
 rhasspyserver_hermes: Publishing 44 bytes(s) to hermes/asr/toggleOn
 rhasspyserver_hermes: -> AsrToggleOn(site_id='default', reason=<AsrToggleReason.PLAY_AUDIO: 'playAudio'>)
 rhasspyserver_hermes: Publishing 44 bytes(s) to hermes/hotword/toggleOn
 rhasspyserver_hermes: -> HotwordToggleOn(site_id='default', reason=<HotwordToggleReason.PLAY_AUDIO: 'playAudio'>)
 rhasspyserver_hermes: Handling AudioPlayFinished (topic=hermes/audioServer/default/playFinished, id=1083dc75-b7ab-4052-af68-162bcf10404b)
 rhasspyserver_hermes: Handling AudioPlayBytes (topic=hermes/audioServer/default/playBytes/e902dbfe-4d65-4270-bdfd-995cb31d0462, id=80e2cac5-ea21-422d-89ea-8ce8209a3626)
 rhasspyserver_hermes: -> AudioPlayBytes(52844 byte(s))
 rhasspyserver_hermes: Publishing 44 bytes(s) to hermes/asr/toggleOff
 rhasspyserver_hermes: -> AsrToggleOff(site_id='default', reason=<AsrToggleReason.PLAY_AUDIO: 'playAudio'>)
 rhasspyserver_hermes: Publishing 44 bytes(s) to hermes/hotword/toggleOff
 rhasspyserver_hermes: -> HotwordToggleOff(site_id='default', reason=<HotwordToggleReason.PLAY_AUDIO: 'playAudio'>)
 rhasspyserver_hermes: Playing 52844 byte(s)
 rhasspyserver_hermes: Handling AudioPlayBytes (topic=hermes/audioServer/default/playBytes/3bf4cb1e-2f60-4115-b117-d13c610673fc, id=80e2cac5-ea21-422d-89ea-8ce8209a3626)
 rhasspyserver_hermes: Sent 260 char(s) to websocket
 rhasspyserver_hermes: Handling NluIntentNotRecognized (topic=hermes/nlu/intentNotRecognized, id=0619ff67-1fb4-4a59-8c54-cdda0b752018)
 rhasspyserver_hermes: Handling NluIntentNotRecognized (topic=hermes/nlu/intentNotRecognized, id=9c3bf6c8-fc31-4340-a93f-e63d3e8916ed)
 rhasspyserver_hermes: <- NluIntentNotRecognized(input='', site_id='default', id='55a62638-7a5e-479b-98b9-a0d9e94e2d5a', custom_data=None, session_id='55a62638-7a5e-479b-98b9-a0d9e94e2d5a')
 rhasspyserver_hermes: Publishing 189 bytes(s) to hermes/nlu/query
 rhasspyserver_hermes: -> NluQuery(input='', site_id='default', id='55a62638-7a5e-479b-98b9-a0d9e94e2d5a', intent_filter=None, session_id='55a62638-7a5e-479b-98b9-a0d9e94e2d5a', wakeword_id=None, lang=None)
 rhasspyserver_hermes: Publishing 74 bytes(s) to hermes/asr/stopListening
 rhasspyserver_hermes: -> AsrStopListening(site_id='default', session_id='55a62638-7a5e-479b-98b9-a0d9e94e2d5a')
 rhasspyserver_hermes: Waiting for intent (session_id=55a62638-7a5e-479b-98b9-a0d9e94e2d5a)
 rhasspyserver_hermes: Handling AsrTextCaptured (topic=hermes/asr/textCaptured, id=9918d31e-b55d-46fe-bb16-7e031b9bbdb4)
 rhasspyserver_hermes: Publishing 180 bytes(s) to hermes/asr/startListening
 rhasspyserver_hermes: -> AsrStartListening(site_id='default', session_id='55a62638-7a5e-479b-98b9-a0d9e94e2d5a', lang=None, stop_on_silence=True, send_audio_captured=True, wakeword_id=None, intent_filter=None)
 rhasspyserver_hermes: Waiting for transcription (session_id=55a62638-7a5e-479b-98b9-a0d9e94e2d5a)

Capture intent
Here we can see sentence isn’t recognized so all slot (text, tokens, intent etc.) values are empty.

2. When I write manually

 rhasspyserver_hermes: Publishing 21 bytes(s) to rhasspy/handle/toggleOn
 rhasspyserver_hermes: -> HandleToggleOn(site_id='default')
 rhasspyserver_hermes: Sent 404 char(s) to websocket
 rhasspyserver_hermes: Handling NluIntent (topic=hermes/intent/Meeting, id=a92c0bf3-d033-45b2-ba31-832a6e2e0cec)
 rhasspyserver_hermes: <- NluIntent(input='Do we have any meeting', intent=Intent(intent_name='Meeting', confidence_score=1.0), site_id='default', id='ffce67eb-0d3d-4ef8-ae54-3cdbd05c0315', slots=[], session_id='ffce67eb-0d3d-4ef8-ae54-3cdbd05c0315', custom_data=None, asr_tokens=[[AsrToken(value='Do', confidence=1.0, range_start=0, range_end=2, time=None), AsrToken(value='we', confidence=1.0, range_start=3, range_end=5, time=None), AsrToken(value='have', confidence=1.0, range_start=6, range_end=10, time=None), AsrToken(value='any', confidence=1.0, range_start=11, range_end=14, time=None), AsrToken(value='meeting', confidence=1.0, range_start=15, range_end=22, time=None)]], asr_confidence=None, raw_input='do we have any meeting', wakeword_id=None, lang=None)
 rhasspyserver_hermes: Publishing 211 bytes(s) to hermes/nlu/query
 rhasspyserver_hermes: -> NluQuery(input='do we have any meeting', site_id='default', id='ffce67eb-0d3d-4ef8-ae54-3cdbd05c0315', intent_filter=None, session_id='ffce67eb-0d3d-4ef8-ae54-3cdbd05c0315', wakeword_id=None, lang=None)
 rhasspyserver_hermes: Publishing 21 bytes(s) to rhasspy/handle/toggleOff
 rhasspyserver_hermes: -> HandleToggleOff(site_id='default')

Capture intent 4
Capture intent 4673×606 6.49 KB

Here It recognized when I write manually.

Help in any form would be appreciated.
Thanks in advance.

2

Can anyone help me in this case, I’m still trying to get it work properly but no improvement.

no intent

Same output though it records my voice but not returning me any intent.

Any help would be really appreciated.

Thanks in advance

3

Can you post more about your configuration?

What are you using for speech to text? I do not see anything about it in your log.

4

I’m using following settings,

Rapsberry Pi 3B+ running Raspbian Buster
Rhasspy 2.5.9 on Docker

Audio recording: arecord (USB PnP microphone)
intent: fsticuffs
speech_to_text: Kaldi
text_to_speech: Flite
hotword: Porcupine
Audio playing: aplay (3.5mm headphone)
Dialogue Management: Rhasspy

I don’t know why it is not transcribing given command into text however, it does return detected intent with json file if I write manually.

Thank you so much for your precious time.

5

OK, I don’t see anything wrong there.

And you say that it can record your Audio. (you can Download the wav file). So it is really weird that Kaldi doesn’t start to parse the audio.

But: You seem to know more than me. I tried to find my log file to compare it to your log file to see the next step that is different, but I can not find the location of the log file.

Did you check if your kaldi process is running. (It is listed as “bash /usr/lib/rhasspy/rhasspy-asr-kaldi-hermes/bin/rhasspy-asr-kaldi-hermes” on my system)

Btw: How are you running Rhasspy? Are you using Docker?

6

Thanks @DanielW for sparing your time and cross checking my log file with your log.
I’m running Rhasspy (version 2.5.9) on Docker (version 20.10.5).

Since two days I’m getting another error while running Kaldi even though I deleted my profile and re-installed rhasspy docker image.
Here it is:

Summary 
[ERROR:2021-03-16 07:08:08,680] rhasspyserver_hermes: Command '['bash', '/usr/lib/rhasspy/rhasspy-asr-kaldi/rhasspyasr_kaldi/kaldi/egs/wsj/s5/utils/prepare_lang.sh', '/profiles/en/kaldi/model/data/local/dict', '<unk>', '/profiles/en/kaldi/model/data/local/lang', '/profiles/en/kaldi/model/data/lang']' returned non-zero exit status 127.
Traceback (most recent call last):
  File "/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/quart/app.py", line 1821, in full_dispatch_request
    result = await self.dispatch_request(request_context)
  File "/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/quart/app.py", line 1869, in dispatch_request
    return await handler(**request_.view_args)
  File "/usr/lib/rhasspy/rhasspy-server-hermes/rhasspyserver_hermes/__main__.py", line 1321, in api_train
    result = await core.train()
  File "/usr/lib/rhasspy/rhasspy-server-hermes/rhasspyserver_hermes/__init__.py", line 471, in train
    raise TrainingFailedException(reason=asr_response.error)
rhasspyserver_hermes.TrainingFailedException: Command '['bash', '/usr/lib/rhasspy/rhasspy-asr-kaldi/rhasspyasr_kaldi/kaldi/egs/wsj/s5/utils/prepare_lang.sh', '/profiles/en/kaldi/model/data/local/dict', '<unk>', '/profiles/en/kaldi/model/data/local/lang', '/profiles/en/kaldi/model/data/lang']' returned non-zero exit status 127.
[ERROR:2021-03-16 07:08:08,671] rhasspyserver_hermes: AsrError(error="Command '['bash', '/usr/lib/rhasspy/rhasspy-asr-kaldi/rhasspyasr_kaldi/kaldi/egs/wsj/s5/utils/prepare_lang.sh', '/profiles/en/kaldi/model/data/local/dict', '<unk>', '/profiles/en/kaldi/model/data/local/lang', '/profiles/en/kaldi/model/data/lang']' returned non-zero exit status 127.", site_id='default', context=None, session_id='6c5e5da7-a2dd-4e8c-898b-7c39df145f08')
[DEBUG:2021-03-16 07:08:08,641] rhasspyserver_hermes: Handling AsrError (topic=hermes/error/asr, id=6fdca2bc-40b5-486c-8491-900c8ee190ab)
[DEBUG:2021-03-16 07:07:59,077] rhasspyserver_hermes: Publishing 791 bytes(s) to rhasspy/asr/default/train
[DEBUG:2021-03-16 07:07:59,069] rhasspyserver_hermes: -> AsrTrain
[DEBUG:2021-03-16 07:07:59,044] rhasspyserver_hermes: Finished writing /profiles/en/intent_graph.pickle.gz
[DEBUG:2021-03-16 07:07:59,022] rhasspyserver_hermes: Writing /profiles/en/intent_graph.pickle.gz
[DEBUG:2021-03-16 07:07:58,787] rhasspynlu.ini_jsgf: Loaded ini file
[DEBUG:2021-03-16 07:07:58,758] rhasspyserver_hermes: Generating intent graph
[DEBUG:2021-03-16 07:07:58,735] rhasspyserver_hermes: Loading sentences from [PosixPath('/usr/lib/rhasspy/rhasspy-profile/rhasspyprofile/profiles/en/sentences.ini')]
[INFO:2021-03-16 07:07:58,713] rhasspyserver_hermes: Starting training
[DEBUG:2021-03-16 07:07:58,340] rhasspyprofile.download: text_to_speech.system larynx dummy = False
[DEBUG:2021-03-16 07:07:58,331] rhasspyprofile.download: speech_to_text.deepspeech.mix_weight >0 0 = False
[DEBUG:2021-03-16 07:07:58,319] rhasspyprofile.download: speech_to_text.kaldi.mix_weight >0 0 = False
[DEBUG:2021-03-16 07:07:58,310] rhasspyprofile.download: speech_to_text.pocketsphinx.mix_weight >0 0 = False
[DEBUG:2021-03-16 07:07:58,300] rhasspyprofile.download: speech_to_text.deepspeech.open_transcription True False = False
[DEBUG:2021-03-16 07:07:58,289] rhasspyprofile.download: speech_to_text.kaldi.open_transcription True False = False
[DEBUG:2021-03-16 07:07:58,276] rhasspyprofile.download: speech_to_text.pocketsphinx.open_transcription True False = False
[DEBUG:2021-03-16 07:07:58,267] rhasspyprofile.download: speech_to_text.system deepspeech kaldi = False
[DEBUG:2021-03-16 07:07:58,261] rhasspyprofile.download: Skipping kaldi/model/phones/silence_phones.txt (/profiles/en/kaldi/model/phones/silence_phones.txt)
[DEBUG:2021-03-16 07:07:58,252] rhasspyprofile.download: Skipping kaldi/model/phones/optional_silence.txt (/profiles/en/kaldi/model/phones/optional_silence.txt)
[DEBUG:2021-03-16 07:07:58,243] rhasspyprofile.download: Skipping kaldi/model/phones/nonsilence_phones.txt (/profiles/en/kaldi/model/phones/nonsilence_phones.txt)
[DEBUG:2021-03-16 07:07:58,232] rhasspyprofile.download: Skipping kaldi/model/phones/extra_questions.txt (/profiles/en/kaldi/model/phones/extra_questions.txt)
[DEBUG:2021-03-16 07:07:58,219] rhasspyprofile.download: Skipping kaldi/model/model/tree (/profiles/en/kaldi/model/model/tree)
[DEBUG:2021-03-16 07:07:58,210] rhasspyprofile.download: Skipping kaldi/model/model/normalization.fst (/profiles/en/kaldi/model/model/normalization.fst)
[DEBUG:2021-03-16 07:07:58,201] rhasspyprofile.download: Skipping kaldi/model/model/final.mdl (/profiles/en/kaldi/model/model/final.mdl)
[DEBUG:2021-03-16 07:07:58,190] rhasspyprofile.download: Skipping kaldi/model/model/den.fst (/profiles/en/kaldi/model/model/den.fst)
[DEBUG:2021-03-16 07:07:58,181] rhasspyprofile.download: Skipping kaldi/model/model/cmvn_opts (/profiles/en/kaldi/model/model/cmvn_opts)
[DEBUG:2021-03-16 07:07:58,172] rhasspyprofile.download: Skipping kaldi/model/extractor/splice_opts (/profiles/en/kaldi/model/extractor/splice_opts)
[DEBUG:2021-03-16 07:07:58,161] rhasspyprofile.download: Skipping kaldi/model/extractor/online_cmvn.conf (/profiles/en/kaldi/model/extractor/online_cmvn.conf)
[DEBUG:2021-03-16 07:07:58,150] rhasspyprofile.download: Skipping kaldi/model/extractor/global_cmvn.stats (/profiles/en/kaldi/model/extractor/global_cmvn.stats)
[DEBUG:2021-03-16 07:07:58,141] rhasspyprofile.download: Skipping kaldi/model/extractor/final.mat (/profiles/en/kaldi/model/extractor/final.mat)
[DEBUG:2021-03-16 07:07:58,132] rhasspyprofile.download: Skipping kaldi/model/extractor/final.ie (/profiles/en/kaldi/model/extractor/final.ie)
[DEBUG:2021-03-16 07:07:58,123] rhasspyprofile.download: Skipping kaldi/model/extractor/final.dubm (/profiles/en/kaldi/model/extractor/final.dubm)
[DEBUG:2021-03-16 07:07:58,109] rhasspyprofile.download: Skipping kaldi/model/conf/online_cmvn.conf (/profiles/en/kaldi/model/conf/online_cmvn.conf)
[DEBUG:2021-03-16 07:07:58,100] rhasspyprofile.download: Skipping kaldi/model/conf/mfcc_hires.conf (/profiles/en/kaldi/model/conf/mfcc_hires.conf)
[DEBUG:2021-03-16 07:07:58,091] rhasspyprofile.download: Skipping kaldi/model/conf/mfcc.conf (/profiles/en/kaldi/model/conf/mfcc.conf)
[DEBUG:2021-03-16 07:07:58,079] rhasspyprofile.download: Skipping kaldi/g2p.corpus (/profiles/en/kaldi/g2p.corpus)
[DEBUG:2021-03-16 07:07:58,070] rhasspyprofile.download: Skipping kaldi/g2p.fst (/profiles/en/kaldi/g2p.fst)
[DEBUG:2021-03-16 07:07:58,059] rhasspyprofile.download: Skipping kaldi/base_dictionary.txt (/profiles/en/kaldi/base_dictionary.txt)
[DEBUG:2021-03-16 07:07:58,050] rhasspyprofile.download: speech_to_text.system kaldi kaldi = True
[DEBUG:2021-03-16 07:07:58,044] rhasspyprofile.download: speech_to_text.system pocketsphinx kaldi = False
[DEBUG:2021-03-16 07:33:43,462] rhasspyserver_hermes: Subscribed to hermes/intent/#
[DEBUG:2021-03-16 07:33:43,402] rhasspyserver_hermes: Subscribed to hermes/asr/textCaptured
[DEBUG:2021-03-16 07:33:43,333] rhasspyserver_hermes: Subscribed to hermes/hotword/+/detected
[DEBUG:2021-03-16 07:33:43,282] rhasspyserver_hermes: Subscribed to rhasspy/asr/default/default/audioCaptured
[DEBUG:2021-03-16 07:33:43,232] rhasspyserver_hermes: Subscribed to hermes/nlu/intentNotRecognized
[DEBUG:2021-03-16 07:33:43,192] rhasspyserver_hermes: Subscribed to hermes/audioServer/default/audioSummary
[DEBUG:2021-03-16 07:33:43,122] rhasspyserver_hermes: Subscribed to hermes/audioServer/default/audioSummary
[DEBUG:2021-03-16 07:33:43,072] rhasspyserver_hermes: Subscribed to rhasspy/asr/default/default/audioCaptured
[DEBUG:2021-03-16 07:33:43,012] rhasspyserver_hermes: Subscribed to hermes/nlu/intentNotRecognized
[DEBUG:2021-03-16 07:33:42,972] rhasspyserver_hermes: Subscribed to hermes/intent/#
[DEBUG:2021-03-16 07:33:42,912] rhasspyserver_hermes: Subscribed to hermes/asr/textCaptured
[DEBUG:2021-03-16 07:33:42,888] rhasspyserver_hermes: Subscribed to hermes/hotword/+/detected
[DEBUG:2021-03-16 07:33:42,792] rhasspyserver_hermes: Connected to MQTT broker
[DEBUG:2021-03-16 07:33:42,652] rhasspyserver_hermes: Connecting to localhost:12183 (retries: 3/10)
[ERROR:2021-03-16 07:33:41,563] rhasspyserver_hermes: mqtt connect
Traceback (most recent call last):
  File "/usr/lib/rhasspy/rhasspy-server-hermes/rhasspyserver_hermes/__init__.py", line 289, in start
    self.client.connect(self.host, self.port)
  File "/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/paho/mqtt/client.py", line 937, in connect
    return self.reconnect()
  File "/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/paho/mqtt/client.py", line 1071, in reconnect
    sock = self._create_socket_connection()
  File "/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/paho/mqtt/client.py", line 3522, in _create_socket_connection
    return socket.create_connection(addr, source_address=source, timeout=self._keepalive)
  File "/usr/local/lib/python3.7/socket.py", line 728, in create_connection
    raise err
  File "/usr/local/lib/python3.7/socket.py", line 716, in create_connection
    sock.connect(sa)
OSError: [Errno 99] Cannot assign requested address

Even I tried pocketsphinx too but It didn’t work as well, ended with kind of same error.

Kindly see:

Summary 
[DEBUG:2021-03-16 09:36:07,656] rhasspyprofile.download: text_to_speech.system larynx nanotts = False
[DEBUG:2021-03-16 09:36:07,596] rhasspyprofile.download: speech_to_text.deepspeech.mix_weight >0 0 = False
[DEBUG:2021-03-16 09:36:07,480] rhasspyprofile.download: speech_to_text.kaldi.mix_weight >0 0 = False
[DEBUG:2021-03-16 09:36:07,400] rhasspyprofile.download: speech_to_text.pocketsphinx.mix_weight >0 0 = False
[DEBUG:2021-03-16 09:36:07,340] rhasspyprofile.download: speech_to_text.deepspeech.open_transcription True False = False
[DEBUG:2021-03-16 09:36:07,260] rhasspyprofile.download: speech_to_text.kaldi.open_transcription True False = False
[DEBUG:2021-03-16 09:36:07,190] rhasspyprofile.download: speech_to_text.pocketsphinx.open_transcription True False = False
[DEBUG:2021-03-16 09:36:07,149] rhasspyprofile.download: speech_to_text.system deepspeech pocketsphinx = False
[DEBUG:2021-03-16 09:36:07,098] rhasspyprofile.download: speech_to_text.system kaldi pocketsphinx = False
[DEBUG:2021-03-16 09:36:07,050] rhasspyprofile.download: Skipping acoustic_model/variances (/profiles/en/acoustic_model/variances)
[DEBUG:2021-03-16 09:36:06,990] rhasspyprofile.download: Skipping acoustic_model/transition_matrices (/profiles/en/acoustic_model/transition_matrices)
[DEBUG:2021-03-16 09:36:06,946] rhasspyprofile.download: Skipping acoustic_model/noisedict (/profiles/en/acoustic_model/noisedict)
[DEBUG:2021-03-16 09:36:06,849] rhasspyprofile.download: Skipping acoustic_model/mixture_weights (/profiles/en/acoustic_model/mixture_weights)
[DEBUG:2021-03-16 09:36:06,790] rhasspyprofile.download: Skipping acoustic_model/means (/profiles/en/acoustic_model/means)
[DEBUG:2021-03-16 09:36:06,709] rhasspyprofile.download: Skipping acoustic_model/mdef (/profiles/en/acoustic_model/mdef)
[DEBUG:2021-03-16 09:36:06,671] rhasspyprofile.download: Skipping acoustic_model/feature_transform (/profiles/en/acoustic_model/feature_transform)
[DEBUG:2021-03-16 09:36:06,596] rhasspyprofile.download: Skipping acoustic_model/feat.params (/profiles/en/acoustic_model/feat.params)
[DEBUG:2021-03-16 09:36:06,519] rhasspyprofile.download: Skipping g2p.corpus (/profiles/en/g2p.corpus)
[DEBUG:2021-03-16 09:36:06,459] rhasspyprofile.download: Skipping g2p.fst (/profiles/en/g2p.fst)
[DEBUG:2021-03-16 09:36:06,399] rhasspyprofile.download: Skipping base_dictionary.txt (/profiles/en/base_dictionary.txt)
[DEBUG:2021-03-16 09:36:06,367] rhasspyprofile.download: speech_to_text.system pocketsphinx pocketsphinx = True
[INFO:2021-03-16 09:35:56,585] rhasspyserver_hermes: Started
[DEBUG:2021-03-16 09:35:56,509] rhasspyserver_hermes: Subscribed to hermes/nlu/intentNotRecognized
[DEBUG:2021-03-16 09:35:56,462] rhasspyserver_hermes: Subscribed to hermes/audioServer/default/audioSummary
[DEBUG:2021-03-16 09:35:56,399] rhasspyserver_hermes: Subscribed to hermes/intent/#
[DEBUG:2021-03-16 09:35:56,329] rhasspyserver_hermes: Subscribed to hermes/asr/textCaptured
[DEBUG:2021-03-16 09:35:56,249] rhasspyserver_hermes: Subscribed to hermes/hotword/+/detected
[DEBUG:2021-03-16 09:35:56,199] rhasspyserver_hermes: Subscribed to rhasspy/asr/default/default/audioCaptured
[DEBUG:2021-03-16 09:35:56,129] rhasspyserver_hermes: Subscribed to hermes/audioServer/default/audioSummary
[DEBUG:2021-03-16 09:35:56,059] rhasspyserver_hermes: Subscribed to rhasspy/asr/default/default/audioCaptured
[DEBUG:2021-03-16 09:35:56,004] rhasspyserver_hermes: Subscribed to hermes/nlu/intentNotRecognized
[DEBUG:2021-03-16 09:35:55,929] rhasspyserver_hermes: Subscribed to hermes/intent/#
[DEBUG:2021-03-16 09:35:55,810] rhasspyserver_hermes: Subscribed to hermes/asr/textCaptured
[DEBUG:2021-03-16 09:35:55,690] rhasspyserver_hermes: Subscribed to hermes/hotword/+/detected
[DEBUG:2021-03-16 09:35:55,598] rhasspyserver_hermes: Connected to MQTT broker
[DEBUG:2021-03-16 09:35:55,427] rhasspyserver_hermes: Connecting to localhost:12183 (retries: 5/10)
[ERROR:2021-03-16 09:35:54,194] rhasspyserver_hermes: mqtt connect
Traceback (most recent call last):
  File "/usr/lib/rhasspy/rhasspy-server-hermes/rhasspyserver_hermes/__init__.py", line 289, in start
    self.client.connect(self.host, self.port)
  File "/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/paho/mqtt/client.py", line 937, in connect
    return self.reconnect()
  File "/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/paho/mqtt/client.py", line 1071, in reconnect
    sock = self._create_socket_connection()
  File "/usr/lib/rhasspy/.venv/lib/python3.7/site-packages/paho/mqtt/client.py", line 3522, in _create_socket_connection
    return socket.create_connection(addr, source_address=source, timeout=self._keepalive)
  File "/usr/local/lib/python3.7/socket.py", line 728, in create_connection
    raise err
  File "/usr/local/lib/python3.7/socket.py", line 716, in create_connection
    sock.connect(sa)
OSError: [Errno 99] Cannot assign requested address

Do you have any idea? Am I doing anything wrong here?

7

That doesn’t look good :frowning:

I didn’t compare my log output with your output, because I do not know were I would find the log output. So my question again:

Can you explain how you are getting those outputs? Is that from a docker run call?

I never had such issues. The issue in your latest post seem to suggest that it can not connect to the MQTT broker.

When you just do the steps in the documenation https://rhasspy.readthedocs.io/en/latest/installation/ you are still getting those errors?

8

Hi,
sorry for late replay, I was trying to fix it and hopefully I found the root cause. It was ASR model, wasn’t getting trained properly on Rpi 3B+ so I had to change it. Now its working as I expected just thing is I had to bought new Rpi. It was really big headache.

Thanks once again.