Reports

Blacklisted phrase (0.5): Thank you
Blacklisted phrase (0.5): thanks
Long answer (-1):
Has code block (-0.5):
Self-answer (0.5):
Low reputation (1):

I'm answering my own question in order to post the final solution to my problem, but it's mainly thanks to Lewis answers and comments below. Thank you Lewis ! the input .wav file must be PCM 16 bit mono, wich can be obtain with "ffmpeg -i "speech3.wav" "outfile.wav" in windows cmd after installing ffmpeg.

import wave
import json
from vosk import Model, KaldiRecognizer, SetLogLevel


#.wav file must be PCM 16-bit mono !

def vosk(wavFile):
    SetLogLevel(0)

    wf = wave.open(wavFile, "rb")

    model = Model(model_path="voskSmallFr", model_name="vosk-model-small-fr-0.22")
    rec = KaldiRecognizer(model, wf.getframerate())
    rec.SetWords(True)
    rec.SetPartialWords(True)
                    
    text = []    
    while True:
        data = wf.readframes(4000)
        if len(data) == 0:
             break
        # if silence detected save result
        if rec.AcceptWaveform(data):
            text.append(json.loads(rec.Result())["text"])
    text.append(json.loads(rec.FinalResult())["text"])

    text=str(text)[2:-2]
    return text



print(vosk("outfile.wav"))

79261520