Merge pull request #110 from pettarin/devel

Added cfw, disabled by default, works

MANIFEST.in

@@ -1,5 +1,6 @@
 recursive-include aeneas/cdtw *
 recursive-include aeneas/cew *
+recursive-include aeneas/cfw *
 recursive-include aeneas/cint *
 recursive-include aeneas/cmfcc *
 recursive-include aeneas/cwave *

README.md

@@ -3,7 +3,7 @@
 **aeneas** is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment).
 
 * Version: 1.6.0.0
-* Date: 2016-09-??
+* Date: 2016-09-26
 * Developed by: [ReadBeyond](http://www.readbeyond.it/)
 * Lead Developer: [Alberto Pettarin](http://www.albertopettarin.it/)
 * License: the GNU Affero General Public License Version 3 (AGPL v3)
@@ -62,7 +62,7 @@ or raw AUD/CSV/SSV/TSV/TXT/XML for further processing.
 3. [FFmpeg](https://www.ffmpeg.org/)
 4. [eSpeak](http://espeak.sourceforge.net/)
 5. Python packages `BeautifulSoup4`, `lxml`, and `numpy`
-6. Python C headers to compile the Python C extensions (optional but strongly recommended)
+6. Python headers to compile the Python C/C++ extensions (optional but strongly recommended)
 7. A shell supporting UTF-8 (optional but strongly recommended)
 
 ### Supported Platforms

README.rst

@@ -5,7 +5,7 @@ aeneas
 synchronize audio and text (aka forced alignment).
 
 -  Version: 1.6.0.0
--  Date: 2016-09-??
+-  Date: 2016-09-26
 -  Developed by: `ReadBeyond <http://www.readbeyond.it/>`__
 -  Lead Developer: `Alberto Pettarin <http://www.albertopettarin.it/>`__
 -  License: the GNU Affero General Public License Version 3 (AGPL v3)
@@ -75,7 +75,7 @@ System Requirements
 3. `FFmpeg <https://www.ffmpeg.org/>`__
 4. `eSpeak <http://espeak.sourceforge.net/>`__
 5. Python packages ``BeautifulSoup4``, ``lxml``, and ``numpy``
-6. Python C headers to compile the Python C extensions (optional but
+6. Python headers to compile the Python C/C++ extensions (optional but
    strongly recommended)
 7. A shell supporting UTF-8 (optional but strongly recommended)
 

aeneas/cew/100_run_driver.sh

@@ -38,6 +38,10 @@ echo "Run 3"
 echo ""
 
 echo "Run 4"
+./cew_driver en "Hello|World|My|Dear|Friend" /tmp/out.wav 2.0 0
+echo ""
+
+echo "Run 5"
 ./cew_driver en "Hello|World|My|Dear|Friend" /tmp/out.wav 2.0 1
 echo ""
 

aeneas/cew/cew_driver.c

@@ -40,6 +40,7 @@ void _usage(const char *prog) {
     printf("\n");
     printf("Example: %s en \"Hello|World|My|Dear|Friend\" /tmp/out.wav 0.0 0\n", prog);
     printf("         %s en \"Hello|World|My|Dear|Friend\" /tmp/out.wav 0.0 1\n", prog);
+    printf("         %s en \"Hello|World|My|Dear|Friend\" /tmp/out.wav 2.0 0\n", prog);
     printf("         %s en \"Hello|World|My|Dear|Friend\" /tmp/out.wav 2.0 1\n", prog);
     printf("\n");
 }

aeneas/cfw/.gitignore

@@ -0,0 +1,5 @@
+build
+__pycache__
+
+*.so
+cfw_driver

aeneas/cfw/000_compile_driver.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+# aeneas is a Python/C library and a set of tools
+# to automagically synchronize audio and text (aka forced alignment)
+#
+# Copyright (C) 2012-2013, Alberto Pettarin (www.albertopettarin.it)
+# Copyright (C) 2013-2015, ReadBeyond Srl   (www.readbeyond.it)
+# Copyright (C) 2015-2016, Alberto Pettarin (www.albertopettarin.it)
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+g++ cfw_driver.cc cfw_func.cc -Ifestival -lFestival -Ispeech_tools -lestools -lestbase -leststring -o cfw_driver -Wall -pedantic
+

aeneas/cfw/100_run_driver.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+# aeneas is a Python/C library and a set of tools
+# to automagically synchronize audio and text (aka forced alignment)
+#
+# Copyright (C) 2012-2013, Alberto Pettarin (www.albertopettarin.it)
+# Copyright (C) 2013-2015, ReadBeyond Srl   (www.readbeyond.it)
+# Copyright (C) 2015-2016, Alberto Pettarin (www.albertopettarin.it)
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+if [ ! -e cfw_driver ]
+then
+    bash 000_compile_driver.sh
+fi
+
+echo "Run 1"
+./cfw_driver
+echo ""
+
+echo "Run 2"
+./cfw_driver "(language_english)" "Hello|World|My|Dear|Friend" /tmp/out.wav 0.0 0
+echo ""
+
+echo "Run 3"
+./cfw_driver "(language_english)" "Hello|World|My|Dear|Friend" /tmp/out.wav 0.0 1
+echo ""
+
+echo "Run 4"
+./cfw_driver "(language_english)" "Hello|World|My|Dear|Friend" /tmp/out.wav 2.0 0
+echo ""
+
+echo "Run 5"
+./cfw_driver "(language_english)" "Hello|World|My|Dear|Friend" /tmp/out.wav 2.0 1
+echo ""
+

aeneas/cfw/800_compile_py.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+# aeneas is a Python/C library and a set of tools
+# to automagically synchronize audio and text (aka forced alignment)
+#
+# Copyright (C) 2012-2013, Alberto Pettarin (www.albertopettarin.it)
+# Copyright (C) 2013-2015, ReadBeyond Srl   (www.readbeyond.it)
+# Copyright (C) 2015-2016, Alberto Pettarin (www.albertopettarin.it)
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+rm -rf build *.so
+python cfw_setup.py build_ext --inplace
+

aeneas/cfw/900_clean.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+# aeneas is a Python/C library and a set of tools
+# to automagically synchronize audio and text (aka forced alignment)
+#
+# Copyright (C) 2012-2013, Alberto Pettarin (www.albertopettarin.it)
+# Copyright (C) 2013-2015, ReadBeyond Srl   (www.readbeyond.it)
+# Copyright (C) 2015-2016, Alberto Pettarin (www.albertopettarin.it)
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+rm -rf build __pycache__ *.so cfw_driver
+

aeneas/cfw/README.md

@@ -0,0 +1,22 @@
+# aeneas.cfw
+
+**aeneas.cfw** is a Python C extension to synthesize text with Festival.
+
+## API
+
+See the [__init__.py](__init__.py) file.
+
+## Compiling the Python C extension locally
+
+```bash
+$ python cfw_setup.py build_ext --inplace
+```
+
+## Compiling the pure C driver program
+
+```bash
+$ bash 000_compile_driver.sh
+```
+
+
+

aeneas/cfw/__init__.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+# coding=utf-8
+
+# aeneas is a Python/C library and a set of tools
+# to automagically synchronize audio and text (aka forced alignment)
+#
+# Copyright (C) 2012-2013, Alberto Pettarin (www.albertopettarin.it)
+# Copyright (C) 2013-2015, ReadBeyond Srl   (www.readbeyond.it)
+# Copyright (C) 2015-2016, Alberto Pettarin (www.albertopettarin.it)
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+"""
+aeneas.cfw is a Python C++ extension to synthesize text with Festival.
+
+The only function provided by this module is:
+
+.. function:: cfw.synthesize_multiple(output_file_path, quit_after, backwards, text)
+
+    Synthesize several text fragments into a single WAVE file.
+
+    The returned tuple ``(sr, synt, anchors)`` contains
+    the sample rate of the output WAVE file,
+    the number of fragments actually synthesized,
+    and a list of time values, each representing
+    the begin time in the output WAVE file
+    of the corresponding text fragment.
+
+    Note that if ``quit_after`` is specified,
+    the number ``synt`` of fragments actually synthesized
+    might be less than the number of fragments in ``text``.
+
+    :param string output_file_path: the path of the WAVE file to be created, UTF-8 encoded
+    :param float quit_after: stop synthesizing after reaching the given duration (in seconds)
+    :param int backwards: if nonzero, synthesize backwards, that is,
+                          starting from the last fragment.
+                          In any case, the fragments in the output WAVE file
+                          will be in natural order.
+                          This option is meaningful only if ``quit_after > 0``.
+    :param list text: a list of ``(voice_code, fragment_text)`` tuples
+                      with the text to be synthesized.
+                      The ``voice_code`` is the the Festival voice code
+                      (e.g., ``(language_english)``, ``(language_scots_gaelic)``,
+                      ``(language_italian)``, etc.).
+                      The ``fragment_text`` must be UTF-8 encoded.
+    :rtype: tuple
+
+"""