Open
Description
I have tried all the possible settings for Models, sample rate, and channels, I am not able to get recognized speech from VOSK, just the empty strings, I have tried the same sample on free speech recognizing websites and they all worked fine with my sample.
def transcribe_audio(audio_file):
global model, recognizer
if not model:
print("Error: Vosk model not initialized.")
return
wf = wave.open(audio_file, "rb")
if wf.getnchannels() != 1 or wf.getsampwidth() != 2 or wf.getcomptype() != "NONE":
print("Audio file must be WAV format mono PCM.")
return
recognizer = KaldiRecognizer(model, wf.getframerate())
while True:
data = wf.readframes(4000)
if len(data) == 0:
break
if recognizer.AcceptWaveform(data):
result = recognizer.Result()
print(result)
# transcription = result[14:-3] # Extract the transcribed text
# print(transcription)
if recognizer.FinalResult():
result = recognizer.FinalResult()
print(result)
# transcription = result[14:-3] # Extract the transcribed text
# print(transcription)
def init_vosk():
global model
if not model:
try:
model = Model(model_name="vosk-model-small-en-us-0.15")
print("Vosk model loaded successfully.")
except Exception as e:
print(f"Error loading Vosk model: {e}")
Metadata
Metadata
Assignees
Labels
No labels