diff options
| -rw-r--r-- | Speak.activity/po/POTFILES.in | 3 | ||||
| -rw-r--r-- | Speak.activity/po/activity.pot | 58 | ||||
| -rw-r--r-- | Speak.activity/po/voice.pot | 149 | ||||
| -rw-r--r-- | dist/speak-4.xo (copied from dist/speak.xo) | bin | 28911 -> 29648 bytes | |||
| -rw-r--r-- | dist/speak-5.xo (renamed from dist/speak.xo) | bin | 28911 -> 32618 bytes | |||
| -rw-r--r-- | docs/TODO.txt | 66 |
6 files changed, 276 insertions, 0 deletions
diff --git a/Speak.activity/po/POTFILES.in b/Speak.activity/po/POTFILES.in new file mode 100644 index 0000000..c41b2e3 --- /dev/null +++ b/Speak.activity/po/POTFILES.in @@ -0,0 +1,3 @@ +encoding: UTF-8 +activity.py +voice.py diff --git a/Speak.activity/po/activity.pot b/Speak.activity/po/activity.pot new file mode 100644 index 0000000..3f13f73 --- /dev/null +++ b/Speak.activity/po/activity.pot @@ -0,0 +1,58 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) YEAR THE PACKAGE'S COPYRIGHT HOLDER +# This file is distributed under the same license as the PACKAGE package. +# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: PACKAGE VERSION\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2008-03-07 08:10+0000\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" +"Language-Team: LANGUAGE <LL@li.org>\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=CHARSET\n" +"Content-Transfer-Encoding: 8bit\n" + +#: ../activity.py:174 +#, python-format +msgid "Hello %s. Type something." +msgstr "" + +#: ../activity.py:334 +msgid "pitch adjusted" +msgstr "" + +#: ../activity.py:337 +msgid "rate adjusted" +msgstr "" + +#: ../activity.py:346 +msgid "Simple" +msgstr "" + +#: ../activity.py:347 +msgid "Waveform" +msgstr "" + +#: ../activity.py:348 +msgid "Frequency" +msgstr "" + +#: ../activity.py:356 +msgid "Round" +msgstr "" + +#: ../activity.py:357 +msgid "Glasses" +msgstr "" + +#: ../activity.py:388 +msgid "mouth changed" +msgstr "" + +#: ../activity.py:409 +msgid "eyes changed" +msgstr "" diff --git a/Speak.activity/po/voice.pot b/Speak.activity/po/voice.pot new file mode 100644 index 0000000..9b8c856 --- /dev/null +++ b/Speak.activity/po/voice.pot @@ -0,0 +1,149 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) YEAR THE PACKAGE'S COPYRIGHT HOLDER +# This file is distributed under the same license as the PACKAGE package. +# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: PACKAGE VERSION\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2008-03-07 08:10+0000\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" +"Language-Team: LANGUAGE <LL@li.org>\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=CHARSET\n" +"Content-Transfer-Encoding: 8bit\n" + +#: ../voice.py:32 +msgid "Brazil" +msgstr "" + +#: ../voice.py:33 +msgid "Swedish" +msgstr "" + +#: ../voice.py:34 +msgid "Icelandic" +msgstr "" + +#: ../voice.py:35 +msgid "Romanian" +msgstr "" + +#: ../voice.py:36 +msgid "Swahili" +msgstr "" + +#: ../voice.py:37 +msgid "Hindi" +msgstr "" + +#: ../voice.py:38 +msgid "Dutch" +msgstr "" + +#: ../voice.py:39 +msgid "Latin" +msgstr "" + +#: ../voice.py:40 +msgid "Hungarian" +msgstr "" + +#: ../voice.py:41 +msgid "Macedonian" +msgstr "" + +#: ../voice.py:42 +msgid "Welsh" +msgstr "" + +#: ../voice.py:43 +msgid "French" +msgstr "" + +#: ../voice.py:44 +msgid "Norwegian" +msgstr "" + +#: ../voice.py:45 +msgid "Russian" +msgstr "" + +#: ../voice.py:46 +msgid "Afrikaans" +msgstr "" + +#: ../voice.py:47 +msgid "Finnish" +msgstr "" + +#: ../voice.py:48 ../voice.py:115 +msgid "Default" +msgstr "" + +#: ../voice.py:49 +msgid "Cantonese" +msgstr "" + +#: ../voice.py:50 +msgid "Scottish" +msgstr "" + +#: ../voice.py:51 +msgid "Greek" +msgstr "" + +#: ../voice.py:52 +msgid "Vietnam" +msgstr "" + +#: ../voice.py:53 +msgid "English" +msgstr "" + +#: ../voice.py:54 +msgid "Lancashire" +msgstr "" + +#: ../voice.py:55 +msgid "Italian" +msgstr "" + +#: ../voice.py:56 +msgid "Portugal" +msgstr "" + +#: ../voice.py:57 +msgid "German" +msgstr "" + +#: ../voice.py:58 +msgid "Whisper" +msgstr "" + +#: ../voice.py:59 +msgid "Croatian" +msgstr "" + +#: ../voice.py:60 +msgid "Czech" +msgstr "" + +#: ../voice.py:61 +msgid "Slovak" +msgstr "" + +#: ../voice.py:62 +msgid "Spanish" +msgstr "" + +#: ../voice.py:63 +msgid "Polish" +msgstr "" + +#: ../voice.py:64 +msgid "Esperanto" +msgstr "" diff --git a/dist/speak.xo b/dist/speak-4.xo Binary files differindex a240395..8d4e442 100644 --- a/dist/speak.xo +++ b/dist/speak-4.xo diff --git a/dist/speak.xo b/dist/speak-5.xo Binary files differindex a240395..d945769 100644 --- a/dist/speak.xo +++ b/dist/speak-5.xo diff --git a/docs/TODO.txt b/docs/TODO.txt new file mode 100644 index 0000000..d053206 --- /dev/null +++ b/docs/TODO.txt @@ -0,0 +1,66 @@ +- collaboration + - if performance is okay, should show multiple faces - one for each person + - if not, then just share settings and let any person type + +- eyes should look some z-distance towards the user + - this should prevent the cross-eyed and mismatched y-coordinate problems + +- i18n + +- speechd + - get newer version with callbacks, list_voices, etc. + - try to insert lots of index_marks + - try to pipe audio back to Speak to get waveform + +- mouth shape should be driven by phonemes + - try C-API callbacks + - we get callbacks for phonemes with really big numbers - not sure how to interpret them + - could use multi-step process: text->human readable phonemes, then add <mark> between each one, then speak + - either way need to handle RETRIEVAL mode and route audio to the right place + - try to wrap espeak API with SWIG + - get per-phoneme callbacks from speechd? + - can we send pre-phonemed [[...]] text to speechd? + +- words/syllables should highlight as it speaks (karaoke-style) + +- repackage face into a widget +- eyes should blink +- there should be a nose +- there should be a Googly vs Normal eye motion (keep y-coords level) +- use XO colors +- mouth doesn't close all the way at the end sometimes? + - especially when using fft and rate is very fast +- large numbers aren't spoken correctly +- eyes should track when dragging sliders in the toolbar + +- adjusting rate, pitch, etc. should say something more informative (like "faster", "slower", etc.) + +- read-a-story mode + - list of stories to read + - easy to add new ones + - play/pause + - remember where you left off + - this sounds like maybe a different activity? + +- predictive typing ala Stephen Hawking's talking computer + - use a simple dictionary for letters, weighted by frequency of use + - use a markov chain for words, seeded with some pre-computed frequencies, but trained by use + +- language translation + I typed "open source machine translation" into Google and spent a couple of hours reading. + Start here: http://events.ccc.de/congress/2006/Fahrplan/events/1701.en.html + This one seems quite nice: http://www.statmt.org/moses/ + The language models + phrase tables are large (200-400 MB) + An open web translation service would be ideal for space, but requires connectivity + Could try: http://www.google.com/language_tools?hl=en + http://www.google.com/support/contact/?translate=1 + http://groups.google.com/group/google-translate + +[done] try speechd API +[done] fix mouth corners by using end caps or a closed shape +[done] eyes should track the text cursor when typing +[done] eyes should float back to center after a while +[done] up/down arrows should cycle through old sentences +[done] text should not disappear until after the sentence is over +[done] should save state to journal + |