Add files via upload

Author: gorpo

speech_recognition/LICENSE-FLAC.txt

@@ -0,0 +1,12 @@
+Copyright (c) 2014-2017, Anthony Zhang <[email protected]>
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

speech_recognition/LICENSE.txt

@@ -0,0 +1,6 @@
+graft speech_recognition
+graft reference
+recursive-exclude speech_recognition *.pyc
+include README.rst
+include LICENSE.txt
+include LICENSE-FLAC.txt

speech_recognition/MANIFEST.in

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+
+import speech_recognition as sr
+
+# obtain path to "english.wav" in the same folder as this script
+from os import path
+AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), "english.wav")
+# AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), "french.aiff")
+# AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), "chinese.flac")
+
+# use the audio file as the audio source
+r = sr.Recognizer()
+with sr.AudioFile(AUDIO_FILE) as source:
+    audio = r.record(source)  # read the entire audio file
+
+# recognize speech using Sphinx
+try:
+    print("Sphinx thinks you said " + r.recognize_sphinx(audio))
+except sr.UnknownValueError:
+    print("Sphinx could not understand audio")
+except sr.RequestError as e:
+    print("Sphinx error; {0}".format(e))
+
+# recognize speech using Google Speech Recognition
+try:
+    # for testing purposes, we're just using the default API key
+    # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
+    # instead of `r.recognize_google(audio)`
+    print("Google Speech Recognition thinks you said " + r.recognize_google(audio))
+except sr.UnknownValueError:
+    print("Google Speech Recognition could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from Google Speech Recognition service; {0}".format(e))
+
+# recognize speech using Google Cloud Speech
+GOOGLE_CLOUD_SPEECH_CREDENTIALS = r"""INSERT THE CONTENTS OF THE GOOGLE CLOUD SPEECH JSON CREDENTIALS FILE HERE"""
+try:
+    print("Google Cloud Speech thinks you said " + r.recognize_google_cloud(audio, credentials_json=GOOGLE_CLOUD_SPEECH_CREDENTIALS))
+except sr.UnknownValueError:
+    print("Google Cloud Speech could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from Google Cloud Speech service; {0}".format(e))
+
+# recognize speech using Wit.ai
+WIT_AI_KEY = "INSERT WIT.AI API KEY HERE"  # Wit.ai keys are 32-character uppercase alphanumeric strings
+try:
+    print("Wit.ai thinks you said " + r.recognize_wit(audio, key=WIT_AI_KEY))
+except sr.UnknownValueError:
+    print("Wit.ai could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from Wit.ai service; {0}".format(e))
+
+# recognize speech using Microsoft Azure Speech
+AZURE_SPEECH_KEY = "INSERT AZURE SPEECH API KEY HERE"  # Microsoft Speech API keys 32-character lowercase hexadecimal strings
+try:
+    print("Microsoft Azure Speech thinks you said " + r.recognize_azure(audio, key=AZURE_SPEECH_KEY))
+except sr.UnknownValueError:
+    print("Microsoft Azure Speech could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from Microsoft Azure Speech service; {0}".format(e))
+
+# recognize speech using Microsoft Bing Voice Recognition
+BING_KEY = "INSERT BING API KEY HERE"  # Microsoft Bing Voice Recognition API keys 32-character lowercase hexadecimal strings
+try:
+    print("Microsoft Bing Voice Recognition thinks you said " + r.recognize_bing(audio, key=BING_KEY))
+except sr.UnknownValueError:
+    print("Microsoft Bing Voice Recognition could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from Microsoft Bing Voice Recognition service; {0}".format(e))
+
+# recognize speech using Houndify
+HOUNDIFY_CLIENT_ID = "INSERT HOUNDIFY CLIENT ID HERE"  # Houndify client IDs are Base64-encoded strings
+HOUNDIFY_CLIENT_KEY = "INSERT HOUNDIFY CLIENT KEY HERE"  # Houndify client keys are Base64-encoded strings
+try:
+    print("Houndify thinks you said " + r.recognize_houndify(audio, client_id=HOUNDIFY_CLIENT_ID, client_key=HOUNDIFY_CLIENT_KEY))
+except sr.UnknownValueError:
+    print("Houndify could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from Houndify service; {0}".format(e))
+
+# recognize speech using IBM Speech to Text
+IBM_USERNAME = "INSERT IBM SPEECH TO TEXT USERNAME HERE"  # IBM Speech to Text usernames are strings of the form XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
+IBM_PASSWORD = "INSERT IBM SPEECH TO TEXT PASSWORD HERE"  # IBM Speech to Text passwords are mixed-case alphanumeric strings
+try:
+    print("IBM Speech to Text thinks you said " + r.recognize_ibm(audio, username=IBM_USERNAME, password=IBM_PASSWORD))
+except sr.UnknownValueError:
+    print("IBM Speech to Text could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from IBM Speech to Text service; {0}".format(e))

speech_recognition/README.rst

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+# NOTE: this example requires PyAudio because it uses the Microphone class
+
+import time
+
+import speech_recognition as sr
+
+
+# this is called from the background thread
+def callback(recognizer, audio):
+    # received audio data, now we'll recognize it using Google Speech Recognition
+    try:
+        # for testing purposes, we're just using the default API key
+        # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
+        # instead of `r.recognize_google(audio)`
+        print("Google Speech Recognition thinks you said " + recognizer.recognize_google(audio))
+    except sr.UnknownValueError:
+        print("Google Speech Recognition could not understand audio")
+    except sr.RequestError as e:
+        print("Could not request results from Google Speech Recognition service; {0}".format(e))
+
+
+r = sr.Recognizer()
+m = sr.Microphone()
+with m as source:
+    r.adjust_for_ambient_noise(source)  # we only need to calibrate once, before we start listening
+
+# start listening in the background (note that we don't have to do this inside a `with` statement)
+stop_listening = r.listen_in_background(m, callback)
+# `stop_listening` is now a function that, when called, stops background listening
+
+# do some unrelated computations for 5 seconds
+for _ in range(50): time.sleep(0.1)  # we're still listening even though the main thread is doing other things
+
+# calling this function requests that the background listener stop listening
+stop_listening(wait_for_stop=False)
+
+# do some more unrelated things
+while True: time.sleep(0.1)  # we're not listening anymore, even though the background thread might still be running for a second or two while cleaning up and stopping

speech_recognition/examples/audio_transcribe.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+
+# NOTE: this example requires PyAudio because it uses the Microphone class
+
+import speech_recognition as sr
+
+# obtain audio from the microphone
+r = sr.Recognizer()
+with sr.Microphone() as source:
+    r.adjust_for_ambient_noise(source)  # listen for 1 second to calibrate the energy threshold for ambient noise levels
+    print("Say something!")
+    audio = r.listen(source)
+
+# recognize speech using Google Speech Recognition
+try:
+    # for testing purposes, we're just using the default API key
+    # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
+    # instead of `r.recognize_google(audio)`
+    print("Google Speech Recognition thinks you said " + r.recognize_google(audio))
+except sr.UnknownValueError:
+    print("Google Speech Recognition could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from Google Speech Recognition service; {0}".format(e))

speech_recognition/examples/background_listening.py

@@ -0,0 +1,11 @@
+#JSGF V1.0;
+
+/**
+ * JSGF Grammar for English counting example
+ */
+
+grammar counting;
+
+public <counting> = ( <digit> ) +;
+
+<digit> = one | two | three | four | five | six | seven ;