refactor!: switch to "pocketsphinx" as package name

cython/CMakeLists.txt

@@ -17,7 +17,7 @@ target_include_directories(
   _pocketsphinx PRIVATE ${CMAKE_BINARY_DIR} # for config.h
   )
 python_extension_module(_pocketsphinx)
-install(TARGETS _pocketsphinx LIBRARY DESTINATION cython/pocketsphinx5)
+install(TARGETS _pocketsphinx LIBRARY DESTINATION cython/pocketsphinx)
 if(NOT USE_INSTALLED_POCKETSPHINX)
-  install(DIRECTORY ${PROJECT_SOURCE_DIR}/model DESTINATION cython/pocketsphinx5)
+  install(DIRECTORY ${PROJECT_SOURCE_DIR}/model DESTINATION cython/pocketsphinx)
 endif()

cython/README.md

@@ -22,7 +22,7 @@ Installation
 You should be able to install this with pip for recent platforms and
 versions of Python:
 
-    pip3 install pocketsphinx5
+    pip3 install pocketsphinx
 
 Alternately, you can also compile it from the source tree.  I highly
 suggest doing this in a virtual environment (replace
@@ -46,7 +46,7 @@ Usage
 
 See the [examples directory](../examples/) for a number of examples of
 using the library from Python.  You can also read the [documentation
-for the Python API](https://pocketsphinx5.readthedocs.io) or [the C
+for the Python API](https://pocketsphinx.readthedocs.io) or [the C
 API](https://cmusphinx.github.io/doc/pocketsphinx/).
 
 It also mostly supports the same APIs as the previous
@@ -60,14 +60,14 @@ microphone.  For example, to do speech-to-text with the default (some
 kind of US English) model:
 
 ```python
-from pocketsphinx5 import LiveSpeech
+from pocketsphinx import LiveSpeech
 for phrase in LiveSpeech(): print(phrase)
 ```
 
 Or to do keyword search:
 
 ```python
-from pocketsphinx5 import LiveSpeech
+from pocketsphinx import LiveSpeech
 
 speech = LiveSpeech(keyphrase='forward', kws_threshold=1e-20)
 for phrase in speech:
@@ -78,7 +78,7 @@ With your model and dictionary:
 
 ```python
 import os
-from pocketsphinx5 import LiveSpeech, get_model_path
+from pocketsphinx import LiveSpeech, get_model_path
 
 speech = LiveSpeech(
     sampling_rate=16000,  # optional
@@ -98,14 +98,14 @@ from a file.  Currently it supports only raw, single-channel, 16-bit
 PCM data in native byte order.
 
 ```python
-from pocketsphinx5 import AudioFile
+from pocketsphinx import AudioFile
 for phrase in AudioFile("goforward.raw"): print(phrase) # => "go forward ten meters"
 ```
 
 An example of a keyword search:
 
 ```python
-from pocketsphinx5 import AudioFile
+from pocketsphinx import AudioFile
 
 audio = AudioFile("goforward.raw", keyphrase='forward', kws_threshold=1e-20)
 for phrase in audio:
@@ -116,7 +116,7 @@ With your model and dictionary:
 
 ```python
 import os
-from pocketsphinx5 import AudioFile, get_model_path
+from pocketsphinx import AudioFile, get_model_path
 
 model_path = get_model_path()
 
@@ -136,7 +136,7 @@ for phrase in audio:
 Convert frame into time coordinates:
 
 ```python
-from pocketsphinx5 import AudioFile
+from pocketsphinx import AudioFile
 
 # Frames per Second
 fps = 100

cython/_pocketsphinx.pyx

@@ -12,11 +12,11 @@ from libc.stdlib cimport malloc, free
 from libc.string cimport memcpy
 import itertools
 import logging
-import pocketsphinx5
+import pocketsphinx
 import os
 cimport _pocketsphinx
 
-LOGGER = logging.getLogger("pocketsphinx5")
+LOGGER = logging.getLogger("pocketsphinx")
 
 cdef class Config:
     """Configuration object for PocketSphinx.
@@ -94,7 +94,7 @@ cdef class Config:
         """
         # Yes, full of race conditions, don't really care (should we?)
         if self.get_string("-hmm") is None:
-            default_am = pocketsphinx5.get_model_path("en-us/en-us")
+            default_am = pocketsphinx.get_model_path("en-us/en-us")
             if os.path.exists(os.path.join(default_am, "means")):
                 self.set_string("-hmm", default_am)
         if (self.get_string("-lm") is None
@@ -103,11 +103,11 @@ cdef class Config:
             and self.get_string("-lmctl") is None
             and self.get_string("-kws") is None
             and self.get_string("-keyphrase") is None):
-            default_lm = pocketsphinx5.get_model_path("en-us/en-us.lm.bin")
+            default_lm = pocketsphinx.get_model_path("en-us/en-us.lm.bin")
             if os.path.exists(default_lm):
                 self.set_string("-lm", default_lm)
         if self.get_string("-dict") is None:
-            default_dict = pocketsphinx5.get_model_path("en-us/cmudict-en-us.dict")
+            default_dict = pocketsphinx.get_model_path("en-us/cmudict-en-us.dict")
             if os.path.exists(default_dict):
                 self.set_string("-dict", default_dict)
 
@@ -319,7 +319,7 @@ cdef class Config:
                 raise ValueError("Unknown type %d in argument %s"
                                  % (base_type, name))
             arg = arg + 1
-            yield pocketsphinx5.Arg(name=name, default=default, doc=doc,
+            yield pocketsphinx.Arg(name=name, default=default, doc=doc,
                                     type=arg_type, required=required)
 
 cdef class LogMath:
@@ -1727,7 +1727,7 @@ def _ps_default_modeldir():
     """Get the system default model path from the PocketSphinx library.
 
     Do not use this function directly, use
-    pocketsphinx5.get_model_path() instead.
+    pocketsphinx.get_model_path() instead.
 
     Returns:
       str: System default model path from PocketSphinx library.

cython/pypocketsphinx-examples.py

@@ -0,0 +1,177 @@
+from pocketsphinx import LiveSpeech
+for phrase in LiveSpeech(): print(phrase)
+from pocketsphinx import LiveSpeech
+
+speech = LiveSpeech(lm=False, keyphrase='forward', kws_threshold=1e-20)
+for phrase in speech:
+    print(phrase.segments(detailed=True))
+
+import os
+from pocketsphinx import LiveSpeech, get_model_path
+
+model_path = get_model_path()
+
+speech = LiveSpeech(
+    verbose=False,
+    sampling_rate=16000,
+    buffer_size=2048,
+    no_search=False,
+    full_utt=False,
+    hmm=os.path.join(model_path, 'en-us'),
+    lm=os.path.join(model_path, 'en-us.lm.bin'),
+    dic=os.path.join(model_path, 'cmudict-en-us.dict')
+)
+
+for phrase in speech:
+    print(phrase)
+
+from pocketsphinx import AudioFile
+for phrase in AudioFile(): print(phrase) # => "go forward ten meters"
+
+from pocketsphinx import AudioFile
+
+audio = AudioFile(lm=False, keyphrase='forward', kws_threshold=1e-20)
+for phrase in audio:
+    print(phrase.segments(detailed=True)) # => "[('forward', -617, 63, 121)]"
+
+import os
+from pocketsphinx import AudioFile, get_model_path, get_data_path
+
+model_path = get_model_path()
+data_path = get_data_path()
+
+config = {
+    'verbose': False,
+    'audio_file': os.path.join(data_path, 'goforward.raw'),
+    'buffer_size': 2048,
+    'no_search': False,
+    'full_utt': False,
+    'hmm': os.path.join(model_path, 'en-us'),
+    'lm': os.path.join(model_path, 'en-us.lm.bin'),
+    'dict': os.path.join(model_path, 'cmudict-en-us.dict')
+}
+
+audio = AudioFile(**config)
+for phrase in audio:
+    print(phrase)
+
+
+from pocketsphinx import AudioFile
+
+# Frames per Second
+fps = 100
+
+for phrase in AudioFile(frate=fps):  # frate (default=100)
+    print('-' * 28)
+    print('| %5s |  %3s  |   %4s   |' % ('start', 'end', 'word'))
+    print('-' * 28)
+    for s in phrase.seg():
+        print('| %4ss | %4ss | %8s |' % (s.start_frame / fps, s.end_frame / fps, s.word))
+    print('-' * 28)
+
+# ----------------------------
+# | start |  end  |   word   |
+# ----------------------------
+# |  0.0s | 0.24s | <s>      |
+# | 0.25s | 0.45s | <sil>    |
+# | 0.46s | 0.63s | go       |
+# | 0.64s | 1.16s | forward  |
+# | 1.17s | 1.52s | ten      |
+# | 1.53s | 2.11s | meters   |
+# | 2.12s |  2.6s | </s>     |
+# ----------------------------
+
+
+from pocketsphinx import Pocketsphinx
+print(Pocketsphinx().decode()) # => "go forward ten meters"
+
+
+
+from __future__ import print_function
+import os
+from pocketsphinx import Pocketsphinx, get_model_path, get_data_path
+
+model_path = get_model_path()
+data_path = get_data_path()
+
+config = {
+    'hmm': os.path.join(model_path, 'en-us'),
+    'lm': os.path.join(model_path, 'en-us.lm.bin'),
+    'dict': os.path.join(model_path, 'cmudict-en-us.dict')
+}
+
+ps = Pocketsphinx(**config)
+ps.decode(
+    audio_file=os.path.join(data_path, 'goforward.raw'),
+    buffer_size=2048,
+    no_search=False,
+    full_utt=False
+)
+
+print(ps.segments()) # => ['<s>', '<sil>', 'go', 'forward', 'ten', 'meters', '</s>']
+print('Detailed segments:', *ps.segments(detailed=True), sep='\n') # => [
+#     word, prob, start_frame, end_frame
+#     ('<s>', 0, 0, 24)
+#     ('<sil>', -3778, 25, 45)
+#     ('go', -27, 46, 63)
+#     ('forward', -38, 64, 116)
+#     ('ten', -14105, 117, 152)
+#     ('meters', -2152, 153, 211)
+#     ('</s>', 0, 212, 260)
+# ]
+
+print(ps.hypothesis())  # => go forward ten meters
+print(ps.probability()) # => -32079
+print(ps.score())       # => -7066
+print(ps.confidence())  # => 0.04042641466841839
+
+print(*ps.best(count=10), sep='\n') # => [
+#     ('go forward ten meters', -28034)
+#     ('go for word ten meters', -28570)
+#     ('go forward and majors', -28670)
+#     ('go forward and meters', -28681)
+#     ('go forward and readers', -28685)
+#     ('go forward ten readers', -28688)
+#     ('go forward ten leaders', -28695)
+#     ('go forward can meters', -28695)
+#     ('go forward and leaders', -28706)
+#     ('go for work ten meters', -28722)
+# ]
+
+
+from pocketsphinx import Pocketsphinx
+
+ps = Pocketsphinx(verbose=True)
+ps.decode()
+
+print(ps.hypothesis())
+
+
+from pocketsphinx import Pocketsphinx
+
+ps = Pocketsphinx(verbose=True, logfn='pocketsphinx.log')
+ps.decode()
+
+print(ps.hypothesis())
+
+import os
+from pocketsphinx import DefaultConfig, Decoder, get_model_path, get_data_path
+
+model_path = get_model_path()
+data_path = get_data_path()
+
+# Create a decoder with a certain model
+config = DefaultConfig()
+config.set_string('-hmm', os.path.join(model_path, 'en-us'))
+config.set_string('-lm', os.path.join(model_path, 'en-us.lm.bin'))
+config.set_string('-dict', os.path.join(model_path, 'cmudict-en-us.dict'))
+decoder = Decoder(config)
+
+# Decode streaming data
+buf = bytearray(1024)
+with open(os.path.join(data_path, 'goforward.raw'), 'rb') as f:
+    decoder.start_utt()
+    while f.readinto(buf):
+        decoder.process_raw(buf, False, False)
+    decoder.end_utt()
+print('Best hypothesis segments:', [seg.word for seg in decoder.seg()])

cython/test/config_test.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 
 import os
-from pocketsphinx5 import Decoder, Config
+from pocketsphinx import Decoder, Config
 import unittest
 
 MODELDIR = os.path.join(os.path.dirname(__file__), "../../model")

cython/test/continuous_test.py

@@ -1,7 +1,7 @@
 #!/usr/bin/python
 
 import os
-from pocketsphinx5 import Decoder
+from pocketsphinx import Decoder
 import unittest
 
 DATADIR = os.path.join(os.path.dirname(__file__), "../../test/data")

cython/test/decoder_test.py

@@ -1,7 +1,7 @@
 #!/usr/bin/python
 
 import os
-from pocketsphinx5 import Decoder
+from pocketsphinx import Decoder
 import unittest
 
 DATADIR = os.path.join(os.path.dirname(__file__), "../../test/data")

cython/test/endpointer_test.py

@@ -3,7 +3,7 @@
 Segment live speech from the default audio device.
 """
 
-from pocketsphinx5 import Vad, Endpointer, set_loglevel
+from pocketsphinx import Vad, Endpointer, set_loglevel
 from contextlib import closing
 import unittest
 import subprocess

cython/test/fsg_test.py

@@ -1,7 +1,7 @@
 #!/usr/bin/python
 
 import unittest
-from pocketsphinx5 import LogMath, FsgModel
+from pocketsphinx import LogMath, FsgModel
 
 
 class FsgTest(unittest.TestCase):

cython/test/jsgf_test.py

@@ -2,7 +2,7 @@
 
 import unittest
 import os
-from pocketsphinx5 import Decoder, Jsgf
+from pocketsphinx import Decoder, Jsgf
 
 DATADIR = os.path.join(os.path.dirname(__file__), "../../test/data")
 

cython/test/kws_test.py

@@ -2,7 +2,7 @@
 
 import unittest
 import sys, os
-from pocketsphinx5 import Decoder
+from pocketsphinx import Decoder
 
 DATADIR = os.path.join(os.path.dirname(__file__), "../../test/data")
 

cython/test/lattice_test.py

@@ -2,7 +2,7 @@
 
 import unittest
 import os
-from pocketsphinx5 import Decoder
+from pocketsphinx import Decoder
 
 DATADIR = os.path.join(os.path.dirname(__file__), "../../test/data")
 

cython/test/lm_test.py

@@ -2,7 +2,7 @@
 
 import unittest
 import os
-from pocketsphinx5 import Decoder, NGramModel
+from pocketsphinx import Decoder, NGramModel
 
 DATADIR = os.path.join(os.path.dirname(__file__), "../../test/data")
 

cython/test/logmath_test.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 
-from pocketsphinx5 import LogMath
+from pocketsphinx import LogMath
 import unittest
 
 

cython/test/phoneme_test.py

@@ -2,7 +2,7 @@
 
 import os
 import unittest
-from pocketsphinx5 import Decoder, get_model_path
+from pocketsphinx import Decoder, get_model_path
 
 DATADIR = os.path.join(os.path.dirname(__file__), "../../test/data")
 

cython/test/pypocketsphinx_test.py

@@ -8,7 +8,7 @@ be compatible.
 """
 
 import os
-from pocketsphinx5 import Pocketsphinx, AudioFile, NGramModel, Jsgf
+from pocketsphinx import Pocketsphinx, AudioFile, NGramModel, Jsgf
 from unittest import TestCase, main
 
 MODELDIR = os.path.join(os.path.dirname(__file__), "../../model")

cython/test/vad_test.py

@@ -3,7 +3,7 @@ import wave
 import os
 from memory_profiler import memory_usage
 
-from pocketsphinx5 import Vad
+from pocketsphinx import Vad
 
 DATADIR = os.path.join(os.path.dirname(__file__), "../../test/data/vad")