mirror of
https://github.com/alphacep/vosk-api.git
synced 2026-02-04 20:45:41 +08:00
32 lines
915 B
Python
Executable File
32 lines
915 B
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
from vosk import Model, KaldiRecognizer
|
|
import sys
|
|
import os
|
|
import wave
|
|
|
|
if not os.path.exists("model"):
|
|
print ("Please download the model from https://alphacephei.com/vosk/models and unpack as 'model' in the current folder.")
|
|
exit (1)
|
|
|
|
wf = wave.open(sys.argv[1], "rb")
|
|
if wf.getnchannels() != 1 or wf.getsampwidth() != 2 or wf.getcomptype() != "NONE":
|
|
print ("Audio file must be WAV format mono PCM.")
|
|
exit (1)
|
|
|
|
model = Model("model")
|
|
|
|
# You can also specify the possible word or phrase list as JSON list, the order doesn't have to be strict
|
|
rec = KaldiRecognizer(model, wf.getframerate(), '["oh one two three four five six seven eight nine zero", "[unk]"]')
|
|
|
|
while True:
|
|
data = wf.readframes(4000)
|
|
if len(data) == 0:
|
|
break
|
|
if rec.AcceptWaveform(data):
|
|
print(rec.Result())
|
|
else:
|
|
print(rec.PartialResult())
|
|
|
|
print(rec.FinalResult())
|