Problem Texttospeech python final.ext.raw sous Raspi3/debian

[lucarnet]

Hello,
I'm testing text to speech (test_speaker.py).
2 problems:

1. Cannot open config mfcc.conf:Solution copying conf/mfcc.conf to the "example" directory fixes the problem (is this normal?)
2. Error opening input stream /home/pi/dev/vosk/vosk-api/python/example/final.ext.raw: No solution
   The problem is created when executing "rec.SetSpkModel(spk_model)"

What's my mistake?
Environment:Raspi3B+/debian11 Python 3.9.2
Thanks.

Probleme mfcc.conf:

pi@pi3:~/dev/vosk/vosk-api/python/example $ python test_speaker.py test.wav
vosk-model-small-en-us-0.15.zip: 100%|█████████████████████████████████████████████████████████████████████████████| 39.3M/39.3M [00:13<00:00, 2.97MB/s]
LOG (VoskAPI:ReadDataFiles():model.cc:213) Decoding params beam=10 max-active=3000 lattice-beam=2
LOG (VoskAPI:ReadDataFiles():model.cc:216) Silence phones 1:2:3:4:5:6:7:8:9:10
LOG (VoskAPI:RemoveOrphanNodes():nnet-nnet.cc:948) Removed 0 orphan nodes.
LOG (VoskAPI:RemoveOrphanComponents():nnet-nnet.cc:847) Removing 0 orphan components.
LOG (VoskAPI:ReadDataFiles():model.cc:248) Loading i-vector extractor from /home/pi/.cache/vosk/vosk-model-small-en-us-0.15/ivector/final.ie
LOG (VoskAPI:ComputeDerivedVars():ivector-extractor.cc:183) Computing derived variables for iVector extractor
LOG (VoskAPI:ComputeDerivedVars():ivector-extractor.cc:204) Done.
LOG (VoskAPI:ReadDataFiles():model.cc:282) Loading HCL and G from /home/pi/.cache/vosk/vosk-model-small-en-us-0.15/graph/HCLr.fst /home/pi/.cache/vosk/vosk-model-small-en-us-0.15/graph/Gr.fst
LOG (VoskAPI:ReadDataFiles():model.cc:308) Loading winfo /home/pi/.cache/vosk/vosk-model-small-en-us-0.15/graph/phones/word_boundary.int
ERROR (VoskAPI:ReadConfigFile():parse-options.cc:463) Cannot open config file: /home/pi/dev/vosk/vosk-api/python/example/mfcc.conf
Traceback (most recent call last):
  File "/home/pi/dev/vosk/vosk-api/python/example/test_speaker.py", line 27, in <module>
    spk_model = SpkModel(SPK_MODEL_PATH)
  File "/usr/local/lib/python3.9/dist-packages/vosk/__init__.py", line 138, in __init__
    raise Exception("Failed to create a speaker model")
Exception: Failed to create a speaker model
pi@pi3:~/dev/vosk/vosk-api/python/example $ 

Problem final.ext.raw:

pi@pi3:~/dev/vosk/vosk-api/python/example $ python test_speaker.py test.wav
LOG (VoskAPI:ReadDataFiles():model.cc:213) Decoding params beam=10 max-active=3000 lattice-beam=2
LOG (VoskAPI:ReadDataFiles():model.cc:216) Silence phones 1:2:3:4:5:6:7:8:9:10
LOG (VoskAPI:RemoveOrphanNodes():nnet-nnet.cc:948) Removed 0 orphan nodes.
LOG (VoskAPI:RemoveOrphanComponents():nnet-nnet.cc:847) Removing 0 orphan components.
LOG (VoskAPI:ReadDataFiles():model.cc:248) Loading i-vector extractor from /home/pi/.cache/vosk/vosk-model-small-en-us-0.15/ivector/final.ie
LOG (VoskAPI:ComputeDerivedVars():ivector-extractor.cc:183) Computing derived variables for iVector extractor
LOG (VoskAPI:ComputeDerivedVars():ivector-extractor.cc:204) Done.
LOG (VoskAPI:ReadDataFiles():model.cc:282) Loading HCL and G from /home/pi/.cache/vosk/vosk-model-small-en-us-0.15/graph/HCLr.fst /home/pi/.cache/vosk/vosk-model-small-en-us-0.15/graph/Gr.fst
LOG (VoskAPI:ReadDataFiles():model.cc:308) Loading winfo /home/pi/.cache/vosk/vosk-model-small-en-us-0.15/graph/phones/word_boundary.int
ERROR (VoskAPI:Input():kaldi-io.cc:756) Error opening input stream /home/pi/dev/vosk/vosk-api/python/example/final.ext.raw
Traceback (most recent call last):
  File "/home/pi/dev/vosk/vosk-api/python/example/test_speaker.py", line 27, in <module>
    spk_model = SpkModel(SPK_MODEL_PATH)
  File "/usr/local/lib/python3.9/dist-packages/vosk/__init__.py", line 138, in __init__
    raise Exception("Failed to create a speaker model")
Exception: Failed to create a speaker model
pi@pi3:~/dev/vosk/vosk-api/python/example $

[nshmyrev]

You need to download speakerid model, it is in the model list.