nodejs with microphone detects something when no one is speaking

Just after start this sample: https://github.com/alphacep/vosk-api/blob/master/nodejs/demo/test_microphone.js

The log is

```
LOG (VoskAPI:ReadDataFiles():model.cc:213) Decoding params beam=13 max-active=7000 lattice-beam=6
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/computer/Github/speech_to_text_sandbox/python/offline_vosk/python_offline_vosk/vosk-model-it-0.22/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:279) Loading HCLG from /home/computer/Github/speech_to_text_sandbox/python/offline_vosk/python_offline_vosk/vosk-model-it-0.22/graph/HCLG.fst
LOG (VoskAPI:ReadDataFiles():model.cc:294) Loading words from /home/computer/Github/speech_to_text_sandbox/python/offline_vosk/python_offline_vosk/vosk-model-it-0.22/graph/words.txt
LOG (VoskAPI:ReadDataFiles():model.cc:303) Loading winfo /home/computer/Github/speech_to_text_sandbox/python/offline_vosk/python_offline_vosk/vosk-model-it-0.22/graph/phones/word_boundary.int
LOG (VoskAPI:ReadDataFiles():model.cc:310) Loading subtract G.fst model from /home/computer/Github/speech_to_text_sandbox/python/offline_vosk/python_offline_vosk/vosk-model-it-0.22/rescore/G.fst
LOG (VoskAPI:ReadDataFiles():model.cc:312) Loading CARPA model from /home/computer/Github/speech_to_text_sandbox/python/offline_vosk/python_offline_vosk/vosk-model-it-0.22/rescore/G.carpa

{ partial: '' }

{ partial: '' }

```

The Buffer line is showing each second (or less). I'm not speaking. I'm in a empty room.