Hello!
I’m new to Rhasspy and would appreciate some help on how my project should be structured. I want to create a voice assistant that calls an API after recognizing the intent and speaking out loud the information returned by the API. This might be basic but I would sure appreciate some guidance on the best way of doing this. I’m developing on my Linux laptop. Thanks in advance!
I think you need to create an intent handler calling the API and returning the text to the TTS API of Rhasspy.
That can be done in several ways, but if your API can simply be called with python I suggest to investigate the rhasspy-hermes-app
https://github.com/rhasspy/rhasspy-hermes-app rhasspy-hermes-app
Yes I would also use rhasspy-hermes-app. There’s an example app that shows you how to call an external API with aiohttp. Note that rhasspy-hermes-app receives intents via MQTT, so you have to add the right connection parameters on the commandline of your app, as shown in the documentation of the basic example.
Thank you @romkabouter @koan for the reply! So I’m trying to get started with the default GetTime intent on the web interface. I have the get_time.py app running in the terminal but nothing happens when the web interface recognizes the GetTime intent. The logs say rhasspyserver_hermes: Sent 370 char(s) to websocket, I realize this might be a silly mistake (maybe not adding the right lines to the profile?) that I made but I’m pretty new to this stuff and would really appreciate some help! Also, any resources/tutorials with steps for creating skills or intent handling would be very helpful! Thanks a ton!
Im assuming you use the internal mqtt broker of rhasspy…
Thus you will need to add the port aswell as the address of your rhasspy instance.
python get_time.py --port 12183 --address 192.168.178.XX
Thanks for your reply @No_one ! I used my IP address but it says TimeApp: error: unrecognized arguments: --address 10.0.2.xx, any idea why that might be? Is there anything I’m doing wrong?
That should be --host.
The python scripts runs successfully now but I still don’t get any responses on the web interface 
What do you mean? You have to talk to Rhasspy 
Then the script makes Rhasspy reply with the time.
Yeah I’m sorry I wasn’t clear, I talked to Rhasspy and it recognized the intent but nothing happened after. I’m a bit confused and just need help setting this up.
If you run the script with the --debug option added, what does it show when it recognized the intent?
And you have checked that the audio output is configured correctly?
[DEBUG:2020-08-14 15:41:52,487] HermesApp: Namespace(debug=True, host='10.0.2.15', log_format='[%(levelname)s:%(asctime)s] %(name)s: %(message)s', password=None, port=12183, site_id=None, tls=False, tls_ca_certs=None, tls_cert_reqs='CERT_REQUIRED', tls_certfile=None, tls_ciphers=None, tls_keyfile=None, tls_version=None, username=None)
[DEBUG:2020-08-14 15:41:52,488] asyncio: Using selector: EpollSelector
[DEBUG:2020-08-14 15:41:52,489] HermesApp: Connecting to 10.0.2.15:12183
[DEBUG:2020-08-14 15:41:52,492] asyncio: Using selector: EpollSelector
[DEBUG:2020-08-14 15:41:52,492] TimeApp: Connected to MQTT broker
[DEBUG:2020-08-14 15:41:52,492] TimeApp: Subscribed to hermes/intent/GetTime
[DEBUG:2020-08-14 15:42:30,487] TimeApp: -> DialogueEndSession(session_id=‘b76fcd1e-2033-4c88-9d94-c77c048b0792’, site_id=‘default’, text=“It’s 15 42”, custom_data=None)
[DEBUG:2020-08-14 15:42:30,494] TimeApp: Publishing 116 bytes(s) to hermes/dialogueManager/endSession
So it seems like it is the scripts is working fine so maybe I have to configure the audio output. When I try entering words and make Rhasspy “speak” it works, is there anything else I need to do?
Check in Rhasspy’s settings whether the site ID really is default.
It is, should I change the text to speech or other settings maybe?
You have the Text To Speech, Audio Playing and Dialogue Management set to Hermes MQTT.
Why?
Hi @romkabouter, thanks for your reply! I had those settings earlier but rhasspy wasn’t speaking out the words then so I tried changing them. Any other ideas as to why the output doesn’t work?
What was your setting for audio play and what was the error in the logs?
Rhasspy logs:
[INFO:2020-08-17 12:58:21,772] rhasspyserver_hermes: Started
[DEBUG:2020-08-17 12:58:21,772] rhasspyserver_hermes: Starting web server at http://0.0.0.0:12101
Running on 0.0.0.0:12101 over http (CTRL + C to quit)
1597683631: New connection from 10.0.2.15 on port 12183.
1597683631: New client connected from 10.0.2.15 as auto-31C3784A-DA08-3142-DF55-D4CB4DB0D8E8 (p2, c1, k60).
1597683640: Socket error on client auto-31C3784A-DA08-3142-DF55-D4CB4DB0D8E8, disconnecting.
1597683646: New connection from 10.0.2.15 on port 12183.
1597683646: New client connected from 10.0.2.15 as auto-A4765CFB-B51F-6B13-17F5-52BE9CEFE4DA (p2, c1, k60).
[DEBUG:2020-08-17 13:01:07,201] rhasspyprofile.download: speech_to_text.system pocketsphinx pocketsphinx = True
[DEBUG:2020-08-17 13:01:07,227] rhasspyprofile.download: Skipping base_dictionary.txt (/home/achintya/.config/rhasspy/profiles/en/base_dictionary.txt)
[DEBUG:2020-08-17 13:01:07,238] rhasspyprofile.download: Skipping g2p.fst (/home/achintya/.config/rhasspy/profiles/en/g2p.fst)
[DEBUG:2020-08-17 13:01:07,243] rhasspyprofile.download: Skipping g2p.corpus (/home/achintya/.config/rhasspy/profiles/en/g2p.corpus)
[DEBUG:2020-08-17 13:01:07,246] rhasspyprofile.download: Skipping acoustic_model/feat.params (/home/achintya/.config/rhasspy/profiles/en/acoustic_model/feat.params)
[DEBUG:2020-08-17 13:01:07,247] rhasspyprofile.download: Skipping acoustic_model/feature_transform (/home/achintya/.config/rhasspy/profiles/en/acoustic_model/feature_transform)
[DEBUG:2020-08-17 13:01:07,247] rhasspyprofile.download: Skipping acoustic_model/mdef (/home/achintya/.config/rhasspy/profiles/en/acoustic_model/mdef)
[DEBUG:2020-08-17 13:01:07,251] rhasspyprofile.download: Skipping acoustic_model/means (/home/achintya/.config/rhasspy/profiles/en/acoustic_model/means)
[DEBUG:2020-08-17 13:01:07,251] rhasspyprofile.download: Skipping acoustic_model/mixture_weights (/home/achintya/.config/rhasspy/profiles/en/acoustic_model/mixture_weights)
[DEBUG:2020-08-17 13:01:07,256] rhasspyprofile.download: Skipping acoustic_model/noisedict (/home/achintya/.config/rhasspy/profiles/en/acoustic_model/noisedict)
[DEBUG:2020-08-17 13:01:07,258] rhasspyprofile.download: Skipping acoustic_model/transition_matrices (/home/achintya/.config/rhasspy/profiles/en/acoustic_model/transition_matrices)
[DEBUG:2020-08-17 13:01:07,259] rhasspyprofile.download: Skipping acoustic_model/variances (/home/achintya/.config/rhasspy/profiles/en/acoustic_model/variances)
[DEBUG:2020-08-17 13:01:07,259] rhasspyprofile.download: speech_to_text.system kaldi pocketsphinx = False
[DEBUG:2020-08-17 13:01:07,262] rhasspyprofile.download: speech_to_text.system deepspeech pocketsphinx = False
[DEBUG:2020-08-17 13:01:07,267] rhasspyprofile.download: speech_to_text.pocketsphinx.open_transcription True False = False
[DEBUG:2020-08-17 13:01:07,269] rhasspyprofile.download: speech_to_text.kaldi.open_transcription True False = False
[DEBUG:2020-08-17 13:01:07,270] rhasspyprofile.download: speech_to_text.deepspeech.open_transcription True False = False
[DEBUG:2020-08-17 13:01:07,270] rhasspyprofile.download: speech_to_text.pocketsphinx.mix_weight >0 0 = False
[DEBUG:2020-08-17 13:01:07,282] rhasspyprofile.download: speech_to_text.kaldi.mix_weight >0 0 = False
[DEBUG:2020-08-17 13:01:07,284] rhasspyprofile.download: speech_to_text.deepspeech.mix_weight >0 0 = False
[DEBUG:2020-08-17 13:01:10,253] rhasspyserver_hermes: Waiting for transcription (session_id=e751cd4d-efd9-4128-8eba-a063e8f25d92)
[DEBUG:2020-08-17 13:01:10,255] rhasspyserver_hermes: Subscribed to hermes/error/asr
[DEBUG:2020-08-17 13:01:10,407] rhasspyserver_hermes: -> AsrStartListening(site_id='default', session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', lang=None, stop_on_silence=True, send_audio_captured=True, wakeword_id=None, intent_filter=None)
[DEBUG:2020-08-17 13:01:10,414] rhasspyserver_hermes: Publishing 180 bytes(s) to hermes/asr/startListening
[DEBUG:2020-08-17 13:01:10,424] rhasspyasr_pocketsphinx_hermes: <- AsrStartListening(site_id='default', session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', lang=None, stop_on_silence=True, send_audio_captured=True, wakeword_id=None, intent_filter=None)
[DEBUG:2020-08-17 13:01:10,425] rhasspyasr_pocketsphinx_hermes: Starting listening (session_id=e751cd4d-efd9-4128-8eba-a063e8f25d92)
[DEBUG:2020-08-17 13:01:10,446] rhasspyasr_pocketsphinx_hermes: Receiving audio
[DEBUG:2020-08-17 13:01:13,615] rhasspyasr_pocketsphinx_hermes: Voice command recorded for session e751cd4d-efd9-4128-8eba-a063e8f25d92 (55680 byte(s))
[DEBUG:2020-08-17 13:01:13,615] rhasspyasr_pocketsphinx_hermes: Transcribing 55724 byte(s) of audio data
INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from /home/achintya/.config/rhasspy/profiles/en/acoustic_model/feat.params
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-allphone
-allphone_ci yes yes
-alpha 0.97 9.700000e-01
-ascale 20.0 2.000000e+01
-aw 1 1
-backtrace no no
-beam 1e-48 1.000000e-48
-bestpath yes yes
-bestpathlw 9.5 9.500000e+00
-ceplen 13 13
-cmn live current
-cmninit 40,3,-1 40,3,-1
-compallsen no no
-dict /home/achintya/.config/rhasspy/profiles/en/dictionary.txt
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict
-feat 1s_c_d_dd 1s_c_d_dd
-featparams
-fillprob 1e-8 1.000000e-08
-frate 100 100
-fsg
-fsgusealtpron yes yes
-fsgusefiller yes yes
-fwdflat yes yes
-fwdflatbeam 1e-64 1.000000e-64
-fwdflatefwid 4 4
-fwdflatlw 8.5 8.500000e+00
-fwdflatsfwin 25 25
-fwdflatwbeam 7e-29 7.000000e-29
-fwdtree yes yes
-hmm /home/achintya/.config/rhasspy/profiles/en/acoustic_model
-input_endian little little
-jsgf
-keyphrase
-kws
-kws_delay 10 10
-kws_plp 1e-1 1.000000e-01
-kws_threshold 1e-30 1.000000e-30
-latsize 5000 5000
-lda
-ldadim 0 0
-lifter 0 22
-lm /home/achintya/.config/rhasspy/profiles/en/language_model.txt
-lmctl
-lmname
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.300000e+02
-lpbeam 1e-40 1.000000e-40
-lponlybeam 7e-29 7.000000e-29
-lw 6.5 6.500000e+00
-maxhmmpf 30000 30000
-maxwpf -1 -1
-mdef
-mean
-mfclogdir
-min_endfr 0 0
-mixw
-mixwfloor 0.0000001 1.000000e-07
-mllr
-mmap yes yes
-ncep 13 13
-nfft 512 512
-nfilt 40 25
-nwpen 1.0 1.000000e+00
-pbeam 1e-48 1.000000e-48
-pip 1.0 1.000000e+00
-pl_beam 1e-10 1.000000e-10
-pl_pbeam 1e-10 1.000000e-10
-pl_pip 1.0 1.000000e+00
-pl_weight 3.0 3.000000e+00
-pl_window 5 5
-rawlogdir
-remove_dc no no
-remove_noise yes yes
-remove_silence yes yes
-round_filters yes yes
-samprate 16000 1.600000e+04
-seed -1 -1
-sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec
-tmat
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 6.800000e+03
-uw 1.0 1.000000e+00
-vad_postspeech 50 50
-vad_prespeech 20 20
-vad_startspeech 10 10
-vad_threshold 3.0 3.000000e+00
-var
-varfloor 0.0001 1.000000e-04
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wbeam 7e-29 7.000000e-29
-wip 0.65 6.500000e-01
-wlen 0.025625 2.562500e-02
INFO: feat.c(715): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='batch', VARNORM='no', AGC='none'
INFO: acmod.c(152): Reading linear feature transformation from /home/achintya/.config/rhasspy/profiles/en/acoustic_model/feature_transform
INFO: mdef.c(518): Reading model definition: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/mdef
INFO: bin_mdef.c(181): Allocating 142124 * 8 bytes (1110 KiB) for CD tree
INFO: tmat.c(149): Reading HMM transition probability matrices: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/transition_matrices
INFO: acmod.c(113): Attempting to use PTM computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/means
INFO: ms_gauden.c(242): 5138 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 32x36
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/variances
INFO: ms_gauden.c(242): 5138 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 32x36
INFO: ms_gauden.c(304): 813 variance values floored
INFO: ptm_mgau.c(803): Number of codebooks exceeds 256: 5138
INFO: acmod.c(115): Attempting to use semi-continuous computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/means
INFO: ms_gauden.c(242): 5138 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 32x36
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/variances
INFO: ms_gauden.c(242): 5138 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 32x36
INFO: ms_gauden.c(304): 813 variance values floored
INFO: acmod.c(117): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/means
INFO: ms_gauden.c(242): 5138 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 32x36
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/variances
INFO: ms_gauden.c(242): 5138 codebook, 1 feature, size:
INFO: ms_gauden.c(244): 32x36
INFO: ms_gauden.c(304): 813 variance values floored
INFO: ms_senone.c(149): Reading senone mixture weights: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/mixture_weights
INFO: ms_senone.c(200): Truncating senone logs3(pdf) values by 10 bits
INFO: ms_senone.c(207): Not transposing mixture weights in memory
INFO: ms_senone.c(268): Read mixture weights for 5138 senones: 1 features x 32 codewords
INFO: ms_senone.c(320): Mapping senones to individual codebooks
INFO: ms_mgau.c(144): The value of topn: 4
INFO: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion penalty 0
INFO: dict.c(320): Allocating 4114 * 32 bytes (128 KiB) for word entries
INFO: dict.c(333): Reading main dictionary: /home/achintya/.config/rhasspy/profiles/en/dictionary.txt
INFO: dict.c(213): Dictionary size 9, allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(336): 9 words read
INFO: dict.c(358): Reading filler dictionary: /home/achintya/.config/rhasspy/profiles/en/acoustic_model/noisedict
INFO: dict.c(213): Dictionary size 18, allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(361): 9 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(406): Allocating 46^3 * 2 bytes (190 KiB) for word-initial triphones
INFO: dict2pid.c(132): Allocated 51152 bytes (49 KiB) for word-final triphones
INFO: dict2pid.c(196): Allocated 51152 bytes (49 KiB) for single-phone word triphones
INFO: ngram_model_trie.c(354): Trying to read LM in trie binary format
INFO: ngram_model_trie.c(365): Header doesn't match
INFO: ngram_model_trie.c(177): Trying to read LM in arpa format
INFO: ngram_model_trie.c(193): LM of order 3
INFO: ngram_model_trie.c(195): #1-grams: 9
INFO: ngram_model_trie.c(195): #2-grams: 10
INFO: ngram_model_trie.c(195): #3-grams: 8
INFO: lm_trie.c(474): Training quantizer
INFO: lm_trie.c(482): Building LM trie
INFO: ngram_search_fwdtree.c(74): Initializing search tree
INFO: ngram_search_fwdtree.c(101): 9 unique initial diphones
INFO: ngram_search_fwdtree.c(186): Creating search channels
INFO: ngram_search_fwdtree.c(323): Max nonroot chan increased to 133
INFO: ngram_search_fwdtree.c(333): Created 9 root, 5 non-root channels, 9 single-phone words
INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25
[DEBUG:2020-08-17 13:01:18,924] rhasspyasr_pocketsphinx.transcribe: Successfully loaded decoder in 5.308273933999999 second(s)
INFO: cmn.c(133): CMN: 57.16 14.67 -6.79 7.85 -3.14 -5.00 -12.12 7.95 3.40 -18.73 5.88 -15.83 11.41
INFO: ngram_search_fwdtree.c(1550): 700 words recognized (5/fr)
INFO: ngram_search_fwdtree.c(1552): 25725 senones evaluated (166/fr)
INFO: ngram_search_fwdtree.c(1556): 14442 channels searched (93/fr), 1325 1st, 12555 last
INFO: ngram_search_fwdtree.c(1559): 1323 words for which last channels evaluated (8/fr)
INFO: ngram_search_fwdtree.c(1561): 537 candidate words for entering last phone (3/fr)
INFO: ngram_search_fwdtree.c(1564): fwdtree 0.15 CPU 0.097 xRT
INFO: ngram_search_fwdtree.c(1567): fwdtree 0.41 wall 0.265 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 11 words
INFO: ngram_search_fwdflat.c(948): 663 words recognized (4/fr)
INFO: ngram_search_fwdflat.c(950): 36871 senones evaluated (238/fr)
INFO: ngram_search_fwdflat.c(952): 22515 channels searched (145/fr)
INFO: ngram_search_fwdflat.c(954): 2165 words searched (13/fr)
INFO: ngram_search_fwdflat.c(957): 686 word transitions (4/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.11 CPU 0.071 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.37 wall 0.239 xRT
[DEBUG:2020-08-17 13:01:19,723] rhasspyasr_pocketsphinx.transcribe: Decoded audio in 0.7921424759999809 second(s)
INFO: ngram_search.c(1250): lattice start node <s>.0 end node </s>.128
INFO: ngram_search.c(1276): Eliminated 3 nodes before end node
INFO: ngram_search.c(1381): Lattice has 207 nodes, 285 links
INFO: ps_lattice.c(1374): Bestpath score: -3045
INFO: ps_lattice.c(1378): Normalizer P(O) = alpha(</s>:128:153) = -156673
INFO: ps_lattice.c(1435): Joint P(O,S) = -191866 P(S|O) = -35193
INFO: ngram_search.c(872): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(875): bestpath 0.00 wall 0.002 xRT
INFO: ngram_search.c(1027): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(1030): bestpath 0.00 wall 0.000 xRT
[DEBUG:2020-08-17 13:01:19,740] rhasspyasr_pocketsphinx_hermes: Transcription(text='what time is it', likelihood=0.029608080097991655, transcribe_seconds=0.7921424759999809, wav_seconds=1.74, tokens=[TranscriptionToken(token='<s>', start_time=0.0, end_time=0.02, likelihood=1.000100016593933), TranscriptionToken(token='what(2)', start_time=0.03, end_time=0.38, likelihood=0.5231039337814566), TranscriptionToken(token='<sil>', start_time=0.39, end_time=0.41, likelihood=0.44357240840395556), TranscriptionToken(token='time', start_time=0.42, end_time=0.71, likelihood=1.0), TranscriptionToken(token='is', start_time=0.72, end_time=0.96, likelihood=1.0), TranscriptionToken(token='it', start_time=0.97, end_time=1.27, likelihood=1.0), TranscriptionToken(token='</s>', start_time=1.28, end_time=1.53, likelihood=1.0)])
[DEBUG:2020-08-17 13:01:19,757] rhasspyasr_pocketsphinx_hermes: -> AsrTextCaptured(text='what time is it', likelihood=0.029608080097991655, seconds=0.7921424759999809, site_id='default', session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', wakeword_id=None, asr_tokens=[[AsrToken(value='<s>', confidence=1.000100016593933, range_start=0, range_end=4, time=AsrTokenTime(start=0.0, end=0.02)), AsrToken(value='what(2)', confidence=0.5231039337814566, range_start=4, range_end=12, time=AsrTokenTime(start=0.03, end=0.38)), AsrToken(value='<sil>', confidence=0.44357240840395556, range_start=12, range_end=18, time=AsrTokenTime(start=0.39, end=0.41)), AsrToken(value='time', confidence=1.0, range_start=18, range_end=23, time=AsrTokenTime(start=0.42, end=0.71)), AsrToken(value='is', confidence=1.0, range_start=23, range_end=26, time=AsrTokenTime(start=0.72, end=0.96)), AsrToken(value='it', confidence=1.0, range_start=26, range_end=29, time=AsrTokenTime(start=0.97, end=1.27)), AsrToken(value='</s>', confidence=1.0, range_start=29, range_end=34, time=AsrTokenTime(start=1.28, end=1.53))]], lang=None)
[DEBUG:2020-08-17 13:01:19,763] rhasspyasr_pocketsphinx_hermes: Publishing 1029 bytes(s) to hermes/asr/textCaptured
[DEBUG:2020-08-17 13:01:19,779] rhasspyasr_pocketsphinx_hermes: -> AsrAudioCaptured(55724 byte(s)) to rhasspy/asr/default/default/audioCaptured
[DEBUG:2020-08-17 13:01:19,809] rhasspyserver_hermes: Handling AsrTextCaptured (topic=hermes/asr/textCaptured, id=887b822f-90b1-44e1-8a7f-fe88f1c4efd8)
[DEBUG:2020-08-17 13:01:19,827] rhasspyserver_hermes: Waiting for intent (session_id=e751cd4d-efd9-4128-8eba-a063e8f25d92)
[DEBUG:2020-08-17 13:01:19,828] rhasspyserver_hermes: Subscribed to hermes/error/nlu
[DEBUG:2020-08-17 13:01:19,832] rhasspyserver_hermes: -> AsrStopListening(site_id='default', session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92')
[DEBUG:2020-08-17 13:01:19,834] rhasspyserver_hermes: Publishing 74 bytes(s) to hermes/asr/stopListening
[DEBUG:2020-08-17 13:01:19,835] rhasspyserver_hermes: -> NluQuery(input='what time is it', site_id='default', id='e751cd4d-efd9-4128-8eba-a063e8f25d92', intent_filter=None, session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', wakeword_id=None, lang=None)
[DEBUG:2020-08-17 13:01:19,837] rhasspydialogue_hermes: <- AsrTextCaptured(text='what time is it', likelihood=0.029608080097991655, seconds=0.7921424759999809, site_id='default', session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', wakeword_id=None, asr_tokens=[[AsrToken(value='<s>', confidence=1.000100016593933, range_start=0, range_end=4, time=AsrTokenTime(start=0.0, end=0.02)), AsrToken(value='what(2)', confidence=0.5231039337814566, range_start=4, range_end=12, time=AsrTokenTime(start=0.03, end=0.38)), AsrToken(value='<sil>', confidence=0.44357240840395556, range_start=12, range_end=18, time=AsrTokenTime(start=0.39, end=0.41)), AsrToken(value='time', confidence=1.0, range_start=18, range_end=23, time=AsrTokenTime(start=0.42, end=0.71)), AsrToken(value='is', confidence=1.0, range_start=23, range_end=26, time=AsrTokenTime(start=0.72, end=0.96)), AsrToken(value='it', confidence=1.0, range_start=26, range_end=29, time=AsrTokenTime(start=0.97, end=1.27)), AsrToken(value='</s>', confidence=1.0, range_start=29, range_end=34, time=AsrTokenTime(start=1.28, end=1.53))]], lang=None)
[DEBUG:2020-08-17 13:01:19,838] rhasspyserver_hermes: Publishing 204 bytes(s) to hermes/nlu/query
[DEBUG:2020-08-17 13:01:19,845] rhasspynlu_hermes: <- NluQuery(input='what time is it', site_id='default', id='e751cd4d-efd9-4128-8eba-a063e8f25d92', intent_filter=None, session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', wakeword_id=None, lang=None)
[DEBUG:2020-08-17 13:01:19,845] rhasspynlu_hermes: Loading /home/achintya/.config/rhasspy/profiles/en/intent_graph.pickle.gz
[WARNING:2020-08-17 13:01:19,851] rhasspydialogue_hermes: Ignoring unknown session e751cd4d-efd9-4128-8eba-a063e8f25d92
[DEBUG:2020-08-17 13:01:19,856] rhasspynlu_hermes: -> NluIntentParsed(input='what time is it', intent=Intent(intent_name='GetTime', confidence_score=1.0), site_id='default', id='e751cd4d-efd9-4128-8eba-a063e8f25d92', slots=[], session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92')
[DEBUG:2020-08-17 13:01:19,861] rhasspynlu_hermes: Publishing 222 bytes(s) to hermes/nlu/intentParsed
[DEBUG:2020-08-17 13:01:19,895] rhasspynlu_hermes: -> NluIntent(input='what time is it', intent=Intent(intent_name='GetTime', confidence_score=1.0), site_id='default', id='e751cd4d-efd9-4128-8eba-a063e8f25d92', slots=[], session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', custom_data=None, asr_tokens=[[AsrToken(value='what', confidence=1.0, range_start=0, range_end=4, time=None), AsrToken(value='time', confidence=1.0, range_start=5, range_end=9, time=None), AsrToken(value='is', confidence=1.0, range_start=10, range_end=12, time=None), AsrToken(value='it', confidence=1.0, range_start=13, range_end=15, time=None)]], asr_confidence=None, raw_input='what time is it', wakeword_id=None, lang=None)
[DEBUG:2020-08-17 13:01:19,898] rhasspynlu_hermes: Publishing 683 bytes(s) to hermes/intent/GetTime
[DEBUG:2020-08-17 13:01:19,922] rhasspydialogue_hermes: <- NluIntent(input='what time is it', intent=Intent(intent_name='GetTime', confidence_score=1.0), site_id='default', id='e751cd4d-efd9-4128-8eba-a063e8f25d92', slots=[], session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', custom_data=None, asr_tokens=[[AsrToken(value='what', confidence=1.0, range_start=0, range_end=4, time=None), AsrToken(value='time', confidence=1.0, range_start=5, range_end=9, time=None), AsrToken(value='is', confidence=1.0, range_start=10, range_end=12, time=None), AsrToken(value='it', confidence=1.0, range_start=13, range_end=15, time=None)]], asr_confidence=None, raw_input='what time is it', wakeword_id=None, lang=None)
[DEBUG:2020-08-17 13:01:19,935] rhasspyserver_hermes: <- NluIntent(input='what time is it', intent=Intent(intent_name='GetTime', confidence_score=1.0), site_id='default', id='e751cd4d-efd9-4128-8eba-a063e8f25d92', slots=[], session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', custom_data=None, asr_tokens=[[AsrToken(value='what', confidence=1.0, range_start=0, range_end=4, time=None), AsrToken(value='time', confidence=1.0, range_start=5, range_end=9, time=None), AsrToken(value='is', confidence=1.0, range_start=10, range_end=12, time=None), AsrToken(value='it', confidence=1.0, range_start=13, range_end=15, time=None)]], asr_confidence=None, raw_input='what time is it', wakeword_id=None, lang=None)
[DEBUG:2020-08-17 13:01:19,944] rhasspyserver_hermes: Handling NluIntent (topic=hermes/intent/GetTime, id=67a41e0a-3c5d-4a32-bb79-f65170a55fd8)
[DEBUG:2020-08-17 13:01:19,945] rhasspydialogue_hermes: <- DialogueEndSession(session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', site_id='default', text="It's 13 01", custom_data=None)
[ERROR:2020-08-17 13:01:19,946] asyncio: Task exception was never retrieved
future: <Task finished coro=<HermesClient.publish_all() done, defined at rhasspy-hermes/rhasspyhermes/client.py:368> exception=AssertionError('No session')>
Traceback (most recent call last):
File "rhasspy-hermes/rhasspyhermes/client.py", line 370, in publish_all
File "rhasspy-dialogue-hermes/rhasspydialogue_hermes/__init__.py", line 668, in on_message
File "rhasspy-dialogue-hermes/rhasspydialogue_hermes/__init__.py", line 375, in handle_end
AssertionError: No session
[DEBUG:2020-08-17 13:01:19,956] rhasspyserver_hermes: Sent 370 char(s) to websocket
[DEBUG:2020-08-17 13:01:20,007] rhasspyasr_pocketsphinx_hermes: <- AsrStopListening(site_id='default', session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92')
[DEBUG:2020-08-17 13:01:20,008] rhasspyasr_pocketsphinx_hermes: Received a total of 309616 byte(s) for WAV data for session e751cd4d-efd9-4128-8eba-a063e8f25d92
[DEBUG:2020-08-17 13:01:20,010] rhasspyasr_pocketsphinx_hermes: Stopping listening (session_id=e751cd4d-efd9-4128-8eba-a063e8f25d92)
Logs from the python script:
python3 examples/time_app.py --port 12183 --host 10.0.2.15 --debug
[DEBUG:2020-08-17 13:00:46,170] HermesApp: Namespace(debug=True, host='10.0.2.15', log_format='[%(levelname)s:%(asctime)s] %(name)s: %(message)s', password=None, port=12183, site_id=None, tls=False, tls_ca_certs=None, tls_cert_reqs='CERT_REQUIRED', tls_certfile=None, tls_ciphers=None, tls_keyfile=None, tls_version=None, username=None)
[DEBUG:2020-08-17 13:00:46,170] asyncio: Using selector: EpollSelector
[DEBUG:2020-08-17 13:00:46,171] HermesApp: Connecting to 10.0.2.15:12183
[DEBUG:2020-08-17 13:00:46,174] asyncio: Using selector: EpollSelector
[DEBUG:2020-08-17 13:00:46,174] TimeApp: Connected to MQTT broker
[DEBUG:2020-08-17 13:00:46,174] TimeApp: Subscribed to hermes/intent/GetTime
[DEBUG:2020-08-17 13:01:19,939] TimeApp: -> DialogueEndSession(session_id='e751cd4d-efd9-4128-8eba-a063e8f25d92', site_id='default', text="It's 13 01", custom_data=None)
[DEBUG:2020-08-17 13:01:19,943] TimeApp: Publishing 116 bytes(s) to hermes/dialogueManager/endSession
and here is a screenshot of my settings:
It seems like everything is working fine but I can’t hear any responses
Please post the whole log file when you post something to your TTS
