2
2
3
3
** aeneas** is a Python library and a set of tools to automagically synchronize audio and text.
4
4
5
- * Version: 1.3.0
6
- * Date: 2015-10-14
5
+ * Version: 1.3.1
6
+ * Date: 2015-10-28
7
7
* Developed by: [ ReadBeyond] ( http://www.readbeyond.it/ )
8
8
* Lead Developer: [ Alberto Pettarin] ( http://www.albertopettarin.it/ )
9
9
* License: the GNU Affero General Public License Version 3 (AGPL v3)
@@ -323,13 +323,14 @@ Changelog: [http://www.readbeyond.it/aeneas/docs/changelog.html](http://www.read
323
323
* Automated detection of audio head/tail
324
324
* MFCC and DTW computed as Python C extensions to reduce the processing time
325
325
* On Linux, ` espeak` called via a Python C extension for faster audio synthesis
326
+ * Output an HTML file (from ` finetuneas` project) for fine tuning the sync map manually
326
327
327
328
# # Limitations and Missing Features
328
329
329
330
* Audio should match the text: large portions of spurious text or audio might produce a wrong sync map
330
331
* Audio is assumed to be spoken: not suitable/YMMV for song captioning
331
332
* No protection against memory trashing if you feed extremely long audio files
332
- * On Mac OS X and Windows, audio synthesis might be slow (tens of minutes) if you have thousands of text fragments
333
+ * On Mac OS X and Windows, audio synthesis might be slow if you have thousands of text fragments
333
334
334
335
# # TODO List
335
336
@@ -340,10 +341,10 @@ Changelog: [http://www.readbeyond.it/aeneas/docs/changelog.html](http://www.read
340
341
* Reporting the alignment score
341
342
* Improving (removing? ) dependency from ` espeak` , ` ffmpeg` , ` ffprobe` executables
342
343
* Multilevel sync map granularity (e.g., multilevel SMIL output)
343
- * Supporting input text encodings other than UTF-8
344
344
* Better documentation
345
345
* Testing other approaches, like HMM
346
346
* Publishing the package on PyPI
347
+ * Publishing the package on Debian repo
347
348
348
349
Would you like to see one of the above points done?
349
350
Consider [sponsoring](# supporting) this project!
@@ -399,6 +400,12 @@ is a verbatim copy from the
399
400
[espeak project](http://espeak.sourceforge.net/).
400
401
See [` licenses/eSpeak.txt` ](licenses/eSpeak.txt) for details.
401
402
403
+ The HTML file ` aeneas/res/finetuneas.html`
404
+ is a verbatim copy from the
405
+ [finetuneas project](https://github.com/ozdefir/finetuneas),
406
+ courtesy of Firat Özdemir.
407
+ See [` licenses/finetuneas.txt` ](licenses/finetuneas.txt) for details.
408
+
402
409
Audio files contained in the unit tests ` aeneas/tests/res/` directory
403
410
are adapted from recordings produced by
404
411
the [LibriVox Project](http://www.librivox.org)
0 commit comments