mirror of
https://github.com/alphacep/vosk-api.git
synced 2026-01-20 20:44:12 +08:00
4209f3a9fe
* methods get_model_by_name, get_model_by_lang, get_model were added into the model class * importing modules changed to using components; introduced constant MODELS_HOME_DIR; simplified code * added new model folders into init; changed samples and transcriber bin for new mode loader * changed back in cli.py lang arg to args.lang * added 3 directories instead of 1 to check for models * cli.py: added 3 args instead of 1 for model; __init__.py: changed script get_model_path for run get_model_by_name/lang inside current directory * deleted default env var * cli.py: changed arg_name; __init__.py: changed const name, changed model loading only for last directory * deleted unused method * changed by_name, by_lang methods, added download_model method * deleted env variable initialization * deleted print() * deteled unused modules * added progress_bar, added folder AppData/Local/vosk for model search * changed download_model methond; added my_hook method
29 lines
632 B
Python
Executable File
29 lines
632 B
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
from vosk import Model, KaldiRecognizer
|
|
import sys
|
|
import json
|
|
import os
|
|
|
|
model = Model(lang="en-us")
|
|
|
|
# Large vocabulary free form recognition
|
|
rec = KaldiRecognizer(model, 16000)
|
|
|
|
# You can also specify the possible word list
|
|
#rec = KaldiRecognizer(model, 16000, "zero oh one two three four five six seven eight nine")
|
|
|
|
wf = open(sys.argv[1], "rb")
|
|
wf.read(44) # skip header
|
|
|
|
while True:
|
|
data = wf.read(4000)
|
|
if len(data) == 0:
|
|
break
|
|
if rec.AcceptWaveform(data):
|
|
res = json.loads(rec.Result())
|
|
print (res['text'])
|
|
|
|
res = json.loads(rec.FinalResult())
|
|
print (res['text'])
|