Update everything

Author: Uberi

LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2014-2015, Anthony Zhang <[email protected]>
+Copyright (c) 2014-2016, 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:

README.rst

@@ -2,15 +2,23 @@
 
 import speech_recognition as sr
 
-# obtain path to "test.wav" in the same folder as this script
+# obtain path to "english.wav" in the same folder as this script
 from os import path
-WAV_FILE = path.join(path.dirname(path.realpath(__file__)), "test.wav")
+WAV_FILE = path.join(path.dirname(path.realpath(__file__)), "english.wav")
 
-# use "test.wav" as the audio source
+# use "english.wav" as the audio source
 r = sr.Recognizer()
 with sr.WavFile(WAV_FILE) as source:
     audio = r.record(source) # read the entire WAV 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

examples/chinese.wav

@@ -10,6 +10,14 @@
     print("Say something!")
     audio = r.listen(source)
 
+# 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

examples/test.wav examples/english.wav

@@ -2,15 +2,23 @@
 
 import speech_recognition as sr
 
-# obtain path to "test.wav" in the same folder as this script
+# obtain path to "english.wav" in the same folder as this script
 from os import path
-WAV_FILE = path.join(path.dirname(path.realpath(__file__)), "test.wav")
+WAV_FILE = path.join(path.dirname(path.realpath(__file__)), "english.wav")
 
-# use "test.wav" as the audio source
+# use "english.wav" as the audio source
 r = sr.Recognizer()
 with sr.WavFile(WAV_FILE) as source:
     audio = r.record(source) # read the entire WAV 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

examples/extended_results.py

@@ -1,19 +1,35 @@
 #!/usr/bin/env python3
 
+import sys, os, stat
+
 from setuptools import setup
+from setuptools.command.install import install
+from distutils import log
+
+import speech_recognition
 
-import sys
 if sys.version_info < (2, 6):
     print("THIS MODULE REQUIRES PYTHON 2.6, 2.7, OR 3.3+. YOU ARE CURRENTLY USING PYTHON {0}".format(sys.version))
     sys.exit(1)
 
-import speech_recognition
+FILES_TO_MARK_EXECUTABLE = ["flac-linux-i386", "flac-mac", "flac-win32.exe"]
+class InstallWithExtraSteps(install):
+    def run(self):
+        install.run(self) # do the original install steps
+
+        # mark the FLAC executables as executable by all users (this fixes occasional issues when file permissions get messed up)
+        for output_path in self.get_outputs():
+            if os.path.basename(output_path) in FILES_TO_MARK_EXECUTABLE:
+                log.info("setting executable permissions on {}".format(output_path))
+                stat_info = os.stat(output_path)
+                os.chmod(output_path, stat_info.st_mode | stat.S_IEXEC)
 
 setup(
     name = "SpeechRecognition",
     version = speech_recognition.__version__,
     packages = ["speech_recognition"],
     include_package_data = True,
+    cmdclass = {"install": InstallWithExtraSteps},
 
     # PyPI metadata
     author = speech_recognition.__author__,

examples/french.wav

@@ -2,10 +2,8 @@
 
 """Library for performing speech recognition with support for Google Speech Recognition, Wit.ai, IBM Speech to Text, and AT&T Speech to Text."""
 
-#wip: provide binaries for PocketSphinx on Windows, or see if the 0.0.5 binaries will work
-
 __author__ = "Anthony Zhang (Uberi)"
-__version__ = "3.1.3"
+__version__ = "4.0.0"
 __license__ = "BSD"
 
 import io, os, subprocess, wave, base64
@@ -401,7 +399,7 @@ def threaded_listen():
                         if running[0]: callback(self, audio)
         def stopper():
             running[0] = False
-            listener_thread.join() # block until the background thread is done
+            listener_thread.join() # block until the background thread is done, which can be up to 1 second
         listener_thread = threading.Thread(target=threaded_listen)
         listener_thread.daemon = True
         listener_thread.start()
@@ -411,14 +409,14 @@ def recognize_sphinx(self, audio_data, language = "en-US", show_all = False):
         """
         Performs speech recognition on ``audio_data`` (an ``AudioData`` instance), using CMU Sphinx.
 
-        The recognition language is determined by ``language``, an IETF language tag like ``"en-US"`` or ``"en-GB"``, defaulting to US English. A list of supported language codes can be found `here <http://stackoverflow.com/questions/14257598/>`__. Basically, language codes can be just the language (``en``), or a language with a dialect (``en-US``). ;wip
+        The recognition language is determined by ``language``, an IETF language tag like ``"en-US"`` or ``"en-GB"``, defaulting to US English. By default, only ``en-US`` is supported. Additional languages can be installed from ;wip
 
         Returns the most likely transcription if ``show_all`` is false (the default). Otherwise, returns the Sphinx ``pocketsphinx.pocketsphinx.Hypothesis`` object generated by Sphinx.
 
         Raises a ``speech_recognition.UnknownValueError`` exception if the speech is unintelligible. Raises a ``speech_recognition.RequestError`` exception if there are any issues with the Sphinx installation.
         """
         assert isinstance(audio_data, AudioData), "`audio_data` must be audio data"
-        assert isinstance(language, str), "`language` must be a string" #wip: do this properly
+        assert isinstance(language, str), "`language` must be a string"
 
         # import the PocketSphinx speech recognition module
         try:
@@ -429,27 +427,27 @@ def recognize_sphinx(self, audio_data, language = "en-US", show_all = False):
 
         language_directory = os.path.join(os.path.dirname(os.path.realpath(__file__)), "pocketsphinx-data", language)
         if not os.path.isdir(language_directory):
-            raise RequestError("missing PocketSphinx model directory: \"{}\"".format(language_directory))
+            raise RequestError("missing PocketSphinx language data directory: \"{0}\"".format(language_directory))
         acoustic_parameters_directory = os.path.join(language_directory, "acoustic-model")
         if not os.path.isdir(acoustic_parameters_directory):
-            raise RequestError("missing PocketSphinx model parameters directory: \"{}\"".format(acoustic_parameters_directory))
+            raise RequestError("missing PocketSphinx language model parameters directory: \"{0}\"".format(acoustic_parameters_directory))
         language_model_file = os.path.join(language_directory, "language-model.lm.bin")
         if not os.path.isfile(language_model_file):
-            raise RequestError("missing PocketSphinx language model file: \"{}\"".format(language_model_file))
+            raise RequestError("missing PocketSphinx language model file: \"{0}\"".format(language_model_file))
         phoneme_dictionary_file = os.path.join(language_directory, "pronounciation-dictionary.dict")
         if not os.path.isfile(phoneme_dictionary_file):
-            raise RequestError("missing PocketSphinx phoneme dictionary file: \"{}\"".format(phoneme_dictionary_file))
+            raise RequestError("missing PocketSphinx phoneme dictionary file: \"{0}\"".format(phoneme_dictionary_file))
 
         # create decoder object
         config = pocketsphinx.Decoder.default_config()
-        config.set_string("-hmm", acoustic_parameters_directory)
+        config.set_string("-hmm", acoustic_parameters_directory) # set the path of the hidden Markov model (HMM) parameter files
         config.set_string("-lm", language_model_file)
         config.set_string("-dict", phoneme_dictionary_file)
         config.set_string("-logfn", os.devnull) # disable logging (logging causes unwanted output in terminal)
         decoder = pocketsphinx.Decoder(config)
 
         # obtain audio data
-        raw_data = audio_data.get_raw_data(convert_rate = 16000, convert_width = 2) # Sphinx requires audio to be 16-bit mono 16 kHz in little-endian format
+        raw_data = audio_data.get_raw_data(convert_rate = 16000, convert_width = 2) # the included language models require audio to be 16-bit mono 16 kHz in little-endian format
 
         # obtain recognition results
         decoder.start_utt() # begin utterance processing