97 lines
2.6 KiB
Python
97 lines
2.6 KiB
Python
#!/usr/bin/env python3
|
|
|
|
# https://github.com/Uberi/speech_recognition/blob/master/examples/microphone_recognition.py
|
|
|
|
|
|
# NOTE: this example requires PyAudio because it uses the Microphone class
|
|
|
|
import speech_recognition as sr
|
|
import time
|
|
import threading
|
|
import queue
|
|
from sys import stderr
|
|
from os import environ
|
|
|
|
class Recognizer(threading.Thread):
|
|
def __init__(self, q):
|
|
threading.Thread.__init__(self)
|
|
self.q = q
|
|
|
|
def run(self):
|
|
while True:
|
|
got = self.q.get()
|
|
if not got:
|
|
break
|
|
self.one(got)
|
|
|
|
def one(self, audio):
|
|
r = sr.Recognizer()
|
|
## recognize speech using Sphinx
|
|
#try:
|
|
# start = time.time()
|
|
# print("Sphinx thinks you said " + r.recognize_sphinx(audio))
|
|
# print("/Sphinx", int(time.time()-start))
|
|
#except sr.UnknownValueError:
|
|
# print("Sphinx could not understand audio")
|
|
#except sr.RequestError as e:
|
|
# print("Sphinx error; {0}".format(e))
|
|
|
|
# recognize speech using whisper
|
|
try:
|
|
start = time.time()
|
|
print(r.recognize_whisper(audio, language="english"))
|
|
print("/Whisper", int(time.time()-start), file=stderr)
|
|
except sr.UnknownValueError:
|
|
print("Whisper could not understand audio")
|
|
except sr.RequestError as e:
|
|
print("Could not request results from Whisper")
|
|
|
|
class Listener():
|
|
def __init__(self):
|
|
if not environ.get("MIC_NAME", None):
|
|
from sys import stdin
|
|
for index, name in enumerate(sr.Microphone.list_microphone_names()):
|
|
print("[{0}] Microphone with name \"{1}\" found for `Microphone(device_index={0})`".format(index, name))
|
|
exit()
|
|
self.name = environ["MIC_NAME"]
|
|
self._mic = None
|
|
|
|
def mic(self):
|
|
if not self._mic:
|
|
self._mic = self.new_mic()
|
|
return self._mic
|
|
|
|
def new_mic(self):
|
|
idx = [idx for idx,v in enumerate(sr.Microphone.list_microphone_names()) if v in self.name.split(",")][0]
|
|
mic = sr.Microphone(device_index=idx)
|
|
mic.__enter__()
|
|
return mic
|
|
|
|
def run(self):
|
|
try:
|
|
return self._run()
|
|
except Exception:
|
|
return None
|
|
|
|
def _run(self):
|
|
mic_timeout=int(environ.get("MIC_TIMEOUT", 5))
|
|
# obtain audio from the microphone
|
|
r = sr.Recognizer()
|
|
#return r.listen(self.mic(), timeout=mic_timeout, phrase_time_limit=mic_timeout)
|
|
return r.record(self.mic(), duration=mic_timeout)
|
|
|
|
q = queue.Queue(maxsize=1)
|
|
l = Listener()
|
|
t = Recognizer(q)
|
|
t.start()
|
|
|
|
try:
|
|
while True:
|
|
got = l.run()
|
|
q.put(got)
|
|
except Exception:
|
|
pass
|
|
finally:
|
|
l._mic.__exit__(None, None, None)
|
|
t.join()
|