README.md aktualisiert
This commit is contained in:
154
README.md
154
README.md
@@ -219,144 +219,28 @@ arecord -D plughw:1,0 --format S16_LE --rate 16000 --channels 1 --duration 5 tes
|
||||
# ausfuehren mit
|
||||
python3 test_simple.py test_mono.wav
|
||||
|
||||
|
||||
|
||||
|
||||
#### test_simple.py
|
||||
|
||||
# vorbereitungen
|
||||
```
|
||||
#!/usr/bin/env python3
|
||||
|
||||
import wave
|
||||
import sys
|
||||
|
||||
from vosk import Model, KaldiRecognizer, SetLogLevel
|
||||
|
||||
# You can set log level to -1 to disable debug messages
|
||||
SetLogLevel(0)
|
||||
|
||||
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.")
|
||||
sys.exit(1)
|
||||
|
||||
model = Model("model") #lang="en-us")
|
||||
|
||||
# You can also init model by name or with a folder path
|
||||
# model = Model(model_name="vosk-model-en-us-0.21")
|
||||
# model = Model("models/en")
|
||||
|
||||
rec = KaldiRecognizer(model, wf.getframerate())
|
||||
rec.SetWords(True)
|
||||
rec.SetPartialWords(True)
|
||||
|
||||
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())
|
||||
mkdir ~/vosk-models
|
||||
```
|
||||
|
||||
### microphone.py
|
||||
Dort alle `*.py`-Dateien und die per `chmod 755` ausführbar gemachte `start_voice.sh` aus diesem Repo einfügen.
|
||||
Damit ohne weitere Interaktion gestartet wird, muss außerdem per `sudo nano /etc/systemd/system/voicerec.service` ein Service angelegt und wie folgt befüllt werden:
|
||||
```
|
||||
#!/usr/bin/env python3
|
||||
[Unit]
|
||||
Description=starten der services fuer die spracherkennung
|
||||
Wants=network-online.target
|
||||
After=network-online.target
|
||||
|
||||
# prerequisites: as described in https://alphacephei.com/vosk/install and also python module `sounddevice` (simply run command `pip install sounddevice`)
|
||||
# Example usage using Dutch (nl) recognition model: `python test_microphone.py -m nl`
|
||||
# For more help run: `python test_microphone.py -h`
|
||||
[Service]
|
||||
Type=simple
|
||||
User=pi
|
||||
Restart=always
|
||||
RestartSec=10
|
||||
StartLimitBurst=10000
|
||||
WorkingDirectory=/home/pi
|
||||
ExecStart=/home/pi/vosk-models/start_voice.sh
|
||||
|
||||
import argparse
|
||||
import queue
|
||||
import sys
|
||||
import sounddevice as sd
|
||||
|
||||
from vosk import Model, KaldiRecognizer
|
||||
|
||||
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")
|
||||
parser.add_argument(
|
||||
"-m", "--model", type=str, help="language model; e.g. en-us, fr, nl; default is en-us")
|
||||
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"])
|
||||
|
||||
if args.model is None:
|
||||
model = Model(lang="de") #"en-us")
|
||||
else:
|
||||
model = Model(lang=args.model)
|
||||
|
||||
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 = KaldiRecognizer(model, args.samplerate)
|
||||
while True:
|
||||
data = q.get()
|
||||
if rec.AcceptWaveform(data):
|
||||
print(rec.Result())
|
||||
else:
|
||||
partialPrint = rec.PartialResult()
|
||||
print(partialPrint)
|
||||
if "licht" in partialPrint and "an" in partialPrint and "hex" in partialPrint:
|
||||
print("SCHALTER EIN!")
|
||||
if "licht" in partialPrint and "aus" in partialPrint and "hex" in partialPrint:
|
||||
print("SCHALTER AUS!")
|
||||
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))
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
EOF
|
||||
```
|
||||
Reference in New Issue
Block a user