mirror of
https://github.com/alphacep/vosk-api.git
synced 2026-02-04 14:38:26 +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
81 lines
2.3 KiB
Python
Executable File
81 lines
2.3 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
import argparse
|
|
import os
|
|
import queue
|
|
import sounddevice as sd
|
|
import vosk
|
|
import sys
|
|
|
|
q = queue.Queue()
|
|
|
|
def int_or_str(text):
|
|
"""Helper function for argument parsing."""
|
|
try:
|
|
return int(text)
|
|
except ValueError:
|
|
return text
|
|
|
|
def callback(indata, frames, time, status):
|
|
"""This is called (from a separate thread) for each audio block."""
|
|
if status:
|
|
print(status, file=sys.stderr)
|
|
q.put(bytes(indata))
|
|
|
|
parser = argparse.ArgumentParser(add_help=False)
|
|
parser.add_argument(
|
|
'-l', '--list-devices', action='store_true',
|
|
help='show list of audio devices and exit')
|
|
args, remaining = parser.parse_known_args()
|
|
if args.list_devices:
|
|
print(sd.query_devices())
|
|
parser.exit(0)
|
|
parser = argparse.ArgumentParser(
|
|
description=__doc__,
|
|
formatter_class=argparse.RawDescriptionHelpFormatter,
|
|
parents=[parser])
|
|
parser.add_argument(
|
|
'-f', '--filename', type=str, metavar='FILENAME',
|
|
help='audio file to store recording to')
|
|
parser.add_argument(
|
|
'-d', '--device', type=int_or_str,
|
|
help='input device (numeric ID or substring)')
|
|
parser.add_argument(
|
|
'-r', '--samplerate', type=int, help='sampling rate')
|
|
args = parser.parse_args(remaining)
|
|
|
|
try:
|
|
if args.samplerate is None:
|
|
device_info = sd.query_devices(args.device, 'input')
|
|
# soundfile expects an int, sounddevice provides a float:
|
|
args.samplerate = int(device_info['default_samplerate'])
|
|
|
|
model = vosk.Model(lang="en-us")
|
|
|
|
if args.filename:
|
|
dump_fn = open(args.filename, "wb")
|
|
else:
|
|
dump_fn = None
|
|
|
|
with sd.RawInputStream(samplerate=args.samplerate, blocksize = 8000, device=args.device, dtype='int16',
|
|
channels=1, callback=callback):
|
|
print('#' * 80)
|
|
print('Press Ctrl+C to stop the recording')
|
|
print('#' * 80)
|
|
|
|
rec = vosk.KaldiRecognizer(model, args.samplerate)
|
|
while True:
|
|
data = q.get()
|
|
if rec.AcceptWaveform(data):
|
|
print(rec.Result())
|
|
else:
|
|
print(rec.PartialResult())
|
|
if dump_fn is not None:
|
|
dump_fn.write(data)
|
|
|
|
except KeyboardInterrupt:
|
|
print('\nDone')
|
|
parser.exit(0)
|
|
except Exception as e:
|
|
parser.exit(type(e).__name__ + ': ' + str(e))
|