whoops

whisper-2023/install.sh

@@ -0,0 +1,7 @@
+#! /bin/bash
+
+sudo apt install portaudio19-dev python3-pyaudio
+python3 -m pip install git+https://github.com/openai/whisper.git soundfile PyAudio SpeechRecognition
+
+sudo apt-get install python3 python3-all-dev python3-pip build-essential swig git libpulse-dev libasound2-dev
+python3 -m pip install pocketsphinx

whisper-2023/microphone_recognition.py

@@ -0,0 +1,73 @@
+#!/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()
+         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"]
+
+   def run(self):
+      mic_timeout=int(environ.get("MIC_TIMEOUT", 5))
+      # obtain audio from the microphone
+      r = sr.Recognizer()
+      idx = [idx for idx,v in enumerate(sr.Microphone.list_microphone_names()) if v in self.name.split(",")][0]
+      with sr.Microphone(device_index=idx) as source:
+          return r.listen(source, timeout=mic_timeout, phrase_time_limit=mic_timeout)
+
+q = queue.Queue(maxsize=1)
+l = Listener()
+t = Recognizer(q)
+t.start()
+
+while True:
+   got = l.run()
+   q.put(got)
+
+t.join()