Speech synthesizers. Catalog of programs for reading voice, text | Speech Synthesis | Text to Speech | Text to speech | TTS
VocalizerVoices_Windows_To_Android.wmv
sm151058 @ 14.11.2012, 08:10
Use captain. More trenchant.
Who jumped from Svoxa at Nuance, much better pronunciation.
Sakramentom enjoyed for many years - it is not better, just by ear used: D
sm151058 @ 14.11.2012, 15:36
Captain - is a Russian engine for Android. Small, smart, defective.http://www.tiflocomp.ru/index.php?mod=arti...=show&id=37РЈworks for me, and on the 2nd Androide
ihelg @ 15.11.2012, 19:15
I read the book now Milena, but apart from excessive (for me) "humanity" voice and the fact that she "woman" strain that it represents the word commas ( "comma"). Who ever thought of how to fix it?
Post has been editedapokrifX - 24.03.13, 16:46
galaxy s2 2.3.5 By enabling NUANCE-MILENA instead of Katie pronunciation better and fewer errors in pronunciation but the sound is much weaker
The hardware used all possibilities and prescribed a maximum sound in the sys
is it possible to increase the sound? It looks like a problem with the volume only galaxy?
The hardware used all possibilities and prescribed a maximum sound in the sys
is it possible to increase the sound? It looks like a problem with the volume only galaxy?
Vinitu2 @ 16.11.2012, 09:32
I did not so I can. If mozhete- correct please.
Yes, everything is simple.
1. Search in Google REGex TESTER. Any open, e.g.http://www.regular-expressions.info/javascriptexample.html
2. Take any of REGex / sdcard / Nuance / languages ​​/ rur / speech / components /rex_rur.dat , eg
/(\ D) (? \ S) feet (\ W | $) / --> " $ 1 $ 2 feet "
3. Trying to drive on the page:
Regexp: (\ d) (? \ S) feet (\ W | $)
Subject string: 100 feet under the keel
Replacement text: $ 1 $ 2 feet
Hit Replace
Get
Result: 100 feet under the keel
3a: Similarly:
Regexp: \ * \ * \ *
Subject string: *** opa-on
Replacement text: (empty)
Hit Replace
Get
Result: opa-on
After editing rex_rur.dat, to re-read it, it is necessary to choose any other TTS, except of Nuance, then again Nuance.
"It is better to lose a day, but then an hour to fly" (C)
Vinitu2 @ 16.11.2012, 10:28
Do not get me quickly, where there is a file rex_rur.dat throw it?
Post has been editedapokrifX - 22.06.13, 17:50
Vinitu2 @ 16.11.2012, 11:00
On the link insert page, click where it take? I understand in rex_rur.dat file, which I found necessary to add a couple of lines. Like me on the page, they find it? Or copy them here, and I'll put in a notebook.
To "eat" *** DB something like:
/\*\*\*/ --> ""
Vinitu2 @ 17.11.2012, 07:53
... identified where Milena says, "comma", is ... (three dots in a row).
/\.\.\./ --> "."
Post has been editedapokrifX - 24.03.13, 18:13
Vocalizer Expressive В© Nuance
The latest version below.
For Russian only neededvocalize_e.tts and voice Milena , Yuri or Katya .
*We need itVocalizer Expressive voices , Vocalizer voices Unsuitable! 
vocalizer_e.tts_1.0.2.3c.zip (1.27 MB)
vocalizer_e.tts_1.0.2.3e.zip(2.42 MB)
vocalizer_e.tts_1.0.2.3f.zip(2.42 MB)
vocalizer_e.tts_1.0.2.3g.zip(2.42 MB)
vocalizer_e.tts_1.0.2.3h.zip(2.51 MB)
vocalizer_e.tts_1.0.2.3i.zip(2.51 MB)
vocalizer_e.tts_1.0.2.3j.zip(2.5 MB)
vocalizer_e.tts_1.0.2.3k.zip(2.68 MB)
vocalizer_e.tts_1.0.2.3l.zip(2.68 MB)
vocalizer_e.tts_1.0.2.3m.zip(2.67 MB)
vocalizer_e.tts_1.0.2.3n.zip(2.68 MB)
vocalizer_e.tts_1.0.2.3o.zip(2.75 MB)
vocalizer_e.tts_1.0.2.3p.zip(2.75 MB)
vocalizer_e.tts_1.0.2.3q.zip(2.75 MB)
vocalizer_e.tts_1.0.2.3r.zip(2.75 MB)
vocalizer_e.tts_1.0.2.3s0.zip(2.75 MB)
vocalizer_e.tts_1.0.2.3t.zip(2.86 MB)
Post has been editedapokrifX - 12.09.16, 08:04
The latest version below.
For Russian only neededvocalize_e.tts and voice Milena , Yuri or Katya .
*We need itVocalizer Expressive voices , Vocalizer voices Unsuitable!
Changes
1.0.2.3t
Libu updated from Nuance, it supports voice of Captain (OS X El Capitan 10.11). Edit * .hrd not needed. My no change.
1.0.2.3s0
Edit for iGo / Primo. When prompted to voice an empty string "", line 1 is replaced by a space "" (0.25 seconds pause.)
1.0.2.3r
Updated libu from Nuance. My no change.
1.0.2.3q
Updated libu from Nuance. My no change.
1.0.2.3p
I adjusted the platform of Vocalizer Expressive SDK to run on Android-e. Prior to that used platform of Vocalizer SDK. I hope that nothing is broken.
For the above ICS and switched on itself TTS UTF-16. In Java and Vocalizer Expressive all strings are stored UTF-16. The Android-ah to ICS, TTS gets the string in UTF-8. Just work in ICS.
Was: Java (UTF-16) ->TTS (UTF-8) ->VocalizerEx (UTF-16)
Was: Java (UTF-16) ->TTS (UTF-16) ->VocalizerEx (UTF-16), i.e. without any extra code conversions.
For the above ICS and switched on itself TTS UTF-16. In Java and Vocalizer Expressive all strings are stored UTF-16. The Android-ah to ICS, TTS gets the string in UTF-8. Just work in ICS.
Was: Java (UTF-16) ->TTS (UTF-8) ->VocalizerEx (UTF-16)
Was: Java (UTF-16) ->TTS (UTF-16) ->VocalizerEx (UTF-16), i.e. without any extra code conversions.
1.0.2.3o
Updated libu from Nuance. My no change. Lieb has recovered markedly, possibly changes will be visible only when there will be a new voice.
1.0.2.3n
Updated libu from Nuance. My no change.
1.0.2.3m
Voices called Milena'Plus, Milena'Premium, Milena 'PremiumHigh, etc.
In previous versions of the TTS, if there is more than one model of voice, they called Milena1, Milena2, etc. To see which model was chosen to vote, it had to go to the adjacent menu.
Updated libu from Nuance to 1.3.1
In previous versions of the TTS, if there is more than one model of voice, they called Milena1, Milena2, etc. To see which model was chosen to vote, it had to go to the adjacent menu.
Updated libu from Nuance to 1.3.1
1.0.2.3l
Updated libu from Nuance. That there is improved or is broken - I do not know.
My no change.
My no change.
1.0.2.3k
Updated libu.
Added languages ​​for the menu.
Added languages ​​for the menu.
Added installation VocalizerEx TTS as a "system application"
Unpackvocalizer_e.tts _ *. apk (It's just a zip archive)
need libylibttsenginevocalizer.so and libdmt_vex.so of lib \ armeabi-v7a \
To install just copy to Android:
need libylibttsenginevocalizer.so and libdmt_vex.so of lib \ armeabi-v7a \
To install just copy to Android:
libttsenginevocalizer.so and libdmt_vex.so ->/ system / lib /
vocalizer_e.tts _ * apk. ->/ system / app /
vocalizer_e.tts _ * apk. ->/ system / app /
1.0.2.3j
Updated Android NDK, finally tightened LLVM libc ++, my liby lost weight by as much as 1/3!
Hopefully, Nuance also shortly switch to LLVM and update his farm.
None of my code changes there.
Added Hungarian language for the menu, if you want to add other languages, PM me.
Hopefully, Nuance also shortly switch to LLVM and update his farm.
None of my code changes there.
Added Hungarian language for the menu, if you want to add other languages, PM me.
1.0.2.3i
TTS mount monitors SDcard on Android 4.X and reads voice.
Previous versions worked so
TTS works fine to connect Android to the PC.
If SDcard "given" PS - all open files are closed forcibly. TTS-in, for example, make a forced restart. He tries to read the voice ... and finds nothing - SDcard available for reading.
If you disable Android by PS - TTS does not restart, because "He does not know" what SDcard became available.
If you try to read the text - TTS bummer.
To bring it to life - you need to restart it. For most it is a small problem.
If SDcard "given" PS - all open files are closed forcibly. TTS-in, for example, make a forced restart. He tries to read the voice ... and finds nothing - SDcard available for reading.
If you disable Android by PS - TTS does not restart, because "He does not know" what SDcard became available.
If you try to read the text - TTS bummer.
To bring it to life - you need to restart it. For most it is a small problem.
The idea is that in this version has to be addressed c TalkBack
TalkBack starts TTS before SDcard mounted, as a result of TTS finds voice and silent.
I think that you have understood that this is done primarily for our blind friends.
I think that you have understood that this is done primarily for our blind friends.
1.0.2.3g / 1.0.2.3h
Updated libs from Nuance. What's new, I do not know. My no change.
1.0.2.3f
Updated libs from Nuance. Any changes to them, I do not know.
A bit simplified internal logic.
Bugs are not corrected, because no log is not received.
A bit simplified internal logic.
Bugs are not corrected, because no log is not received.
1.0.2.3e
Added libu for ARM7 - Premium High voices began to be loadedmuch faster .
Redid choice votes for ICS - if one voice then the choice is not shown (there is nothing to choose)
If there is such
Milena bet3, dri80_1175mrf22 and full_vssq5f22
Yuri bet3 and full_vssq5f22
Will have a choice:
Russian: Milena bet3, dri80_1175mrf22, full_vssq5f22 and Yuri bet3 and full_vssq5f22 (all 5)
Russian (Russia): Milena bet3, dri80_1175mrf22, full_vssq5f22 and Yuri bet3 and full_vssq5f22 (all 5)
Russian (Russia) Milena: Milena bet3, dri80_1175mrf22, full_vssq5f22 (all 3 Milena)
Russian (Russia) Yuri: Yuri bet3 and full_vssq5f22 (both of Yuri)
It is necessary for iGo, which may request the voice more precisely: rus-RUS-Milena
Bugs are not corrected.
Someone said that the biggest and the smallest speed TTS silent.
I was not able to reproduce the log is also not sent.
If anyone has a problem yet - PM me log.
Redid choice votes for ICS - if one voice then the choice is not shown (there is nothing to choose)
If there is such
Milena bet3, dri80_1175mrf22 and full_vssq5f22
Yuri bet3 and full_vssq5f22
Will have a choice:
Russian: Milena bet3, dri80_1175mrf22, full_vssq5f22 and Yuri bet3 and full_vssq5f22 (all 5)
Russian (Russia): Milena bet3, dri80_1175mrf22, full_vssq5f22 and Yuri bet3 and full_vssq5f22 (all 5)
Russian (Russia) Milena: Milena bet3, dri80_1175mrf22, full_vssq5f22 (all 3 Milena)
Russian (Russia) Yuri: Yuri bet3 and full_vssq5f22 (both of Yuri)
It is necessary for iGo, which may request the voice more precisely: rus-RUS-Milena
Bugs are not corrected.
Someone said that the biggest and the smallest speed TTS silent.
I was not able to reproduce the log is also not sent.
If anyone has a problem yet - PM me log.
Pictures
Same as forNuance Vocalizer
If TTS is not running, andthere is a desire to understand
PM melogcat log:
1. With filter VxTTS
2. At the start VocalizerEx TTS
* How should look like, see the log.Ivona tts
1. With filter VxTTS
2. At the start VocalizerEx TTS
* How should look like, see the log.Ivona tts
vauto_logging.hdr
vauto_logging.hdr / ve_logging.hdr for Vocalizer Expressive on the windows - works, and on Android -NOT . Tried everything, without the SDK does not understand ...
previous versions
vocalizer_e.tts_1.0.2.3c.zip (1.27 MB) vocalizer_e.tts_1.0.2.3e.zip(2.42 MB)vocalizer_e.tts_1.0.2.3f.zip(2.42 MB)vocalizer_e.tts_1.0.2.3g.zip(2.42 MB)vocalizer_e.tts_1.0.2.3h.zip(2.51 MB)vocalizer_e.tts_1.0.2.3i.zip(2.51 MB)vocalizer_e.tts_1.0.2.3j.zip(2.5 MB)vocalizer_e.tts_1.0.2.3k.zip(2.68 MB)vocalizer_e.tts_1.0.2.3l.zip(2.68 MB)vocalizer_e.tts_1.0.2.3m.zip(2.67 MB)vocalizer_e.tts_1.0.2.3n.zip(2.68 MB)vocalizer_e.tts_1.0.2.3o.zip(2.75 MB)vocalizer_e.tts_1.0.2.3p.zip(2.75 MB)vocalizer_e.tts_1.0.2.3q.zip(2.75 MB)vocalizer_e.tts_1.0.2.3r.zip(2.75 MB)vocalizer_e.tts_1.0.2.3s0.zip(2.75 MB)Attached files
vocalizer_e.tts_1.0.2.3t.zip(2.86 MB)Post has been editedapokrifX - 12.09.16, 08:04
dimokis @ 18.11.2012, 12:23
Milena says "comma" in the case where after the punctuation mark should dash
For example:
Ivan was silent.
-Why are you silent? - asked Yura.
read as "Ivan was silent silent comma comma then I asked him Jura"
Damn, when a lot of dialogue in the book is so annoying is the "comma" when pronounced in three words ...
For example:
Ivan was silent.
-Why are you silent? - asked Yura.
read as "Ivan was silent silent comma comma then I asked him Jura"
Damn, when a lot of dialogue in the book is so annoying is the "comma" when pronounced in three words ...
Ivan was silent
Or you can check in other chitalke?
dimokis @ 18.11.2012, 12:23
Yet. When the book comes across the word "days" instead of the word Milena says "Your account Tom-tom traffic ends in ..."
Vinitu2 @ 18.11.2012, 14:19
I have not said Milena comma, except in cases of ...
Ivan was silent ... ...
-What are silent - and asked him Jura.
-What are you silent? -... asked Jora.
-What are silent - and asked him Jura.
-What are you silent? -... asked Jora.
Checked, cleaned regex:
/([\?!])-/ --> "$1"
Vinitu2 @ 18.11.2012, 14:19
About TomTom also heard a couple of times, but did not think that this is connected with the text. I thought it was in the most prog laid.
Program for editing dictionaries:Nuance Vocalizer Studio . I have not it. : Blush:
Post has been editedapokrifX - 19.11.12, 18:52
Ivona @ Amazon.com for ICS +
The latest version below.
For Russian only neededivona.tts and voice Tatyana and Maxim .
ivona.tts_1.0.0.0a8.zip(80.88 Kb)
lexicon_examples.zip(1.4 KB)
ivona.tts_1.0.0.0a8a.zip(80.84 Kb)
ivona.tts_1.0.0.0b.zip(71.79 KB)
ivona.tts_1.0.0.0b1.zip(71.64 KB)
Post has been editedapokrifX - 23.07.17, 23:17
The latest version below.
For Russian only neededivona.tts and voice Tatyana and Maxim .
Instructions
Installing dyuzhe complex, 12 steps. If you can not read or do not read the instructions on the principle that it is not for you!
* Ivona.tts_1.0.0.0b.apk works with voices 1.6.68 and higher only!
* Ivona.tts_1.0.0.0b.apk works with voices 1.6.68 and higher only!
steps.txt
0. create folder ivona oninternal sdcard, for next steps I assume it's / Sdcard / ivona /
1. download rus.rus.tatyana. *. Rar
2. unpack it into the folder created in step # 0
3. make sure you have four files there (in/sdcard/ivona/rus.rus.tatyana/)
lang_ru_ru.dat
libttsivonavoice.so
libvoice_ru_tatyana.so
vox_ru_tatyana22i
4. copylang_ru_ru.datfile twice:
lang_ru_ru.dat ->lang_ru_ru_tatyana .dat
lang_ru_ru.dat ->voice_ru_ru_tatyana .dat
5. optionaly, add regular expressions lexicon (s) * .lex (russian.lex) And PLS lexicon (s) * .pls (russian.pls) To your taste.
6. repeat steps 3..5 for other voices, if needed
7. install IvonaTTS.apk
8. select Ivona TTS as default TTS
9. go to setting / install voice data / select folder you created in step # 0 (i.e./ Sdcard / ivona /, not/sdcard/ivona/rus.rus.tatyana/) / Click OK / check log / click Close
A. exit to home screen
B. go to Ivona TTS setting again / Language / click on Voice you want. if Voice list is empty - restart TTS (or reboot android)
C. go back / click on "Listen to an example", it should work now
* To restart TTS it might be sufficient to change screen orientation while in Text-to-Speech setting screen.
1. download rus.rus.tatyana. *. Rar
2. unpack it into the folder created in step # 0
3. make sure you have four files there (in/sdcard/ivona/rus.rus.tatyana/)
lang_ru_ru.dat
libttsivonavoice.so
libvoice_ru_tatyana.so
vox_ru_tatyana22i
4. copylang_ru_ru.datfile twice:
lang_ru_ru.dat ->lang_ru_ru_tatyana .dat
lang_ru_ru.dat ->voice_ru_ru_tatyana .dat
5. optionaly, add regular expressions lexicon (s) * .lex (russian.lex) And PLS lexicon (s) * .pls (russian.pls) To your taste.
6. repeat steps 3..5 for other voices, if needed
7. install IvonaTTS.apk
8. select Ivona TTS as default TTS
9. go to setting / install voice data / select folder you created in step # 0 (i.e./ Sdcard / ivona /, not/sdcard/ivona/rus.rus.tatyana/) / Click OK / check log / click Close
A. exit to home screen
B. go to Ivona TTS setting again / Language / click on Voice you want. if Voice list is empty - restart TTS (or reboot android)
C. go back / click on "Listen to an example", it should work now
* To restart TTS it might be sufficient to change screen orientation while in Text-to-Speech setting screen.
uno mas
0. Create a folder on ivonainternal sdcard, eg / sdcard / ivona /
1. Download rus.rus.tatyana. *. Rar
2. extract it to the folder you created in step в„–0
3. Make sure that you have the following 4 files in /sdcard/ivona/rus.rus.tatyana/
lang_ru_ru.dat
libttsivonavoice.so
libvoice_ru_tatyana.so
vox_ru_tatyana22i
4. copy the filelang_ru_ru.dattwice
lang_ru_ru.dat ->lang_ru_ru_tatyana .dat
lang_ru_ru.dat ->voice_ru_ru_tatyana .dat
5. to taste add the lexicon (s) regular expressions * .lex (russian.lex) and PLS lexicon (s) * .pls (russian.pls)
6. if you need other voices repeat the steps to 1..5
7. Set IvonaTTS.apk
8. enter the setup Text-To-Speech, select "Ivona TTS" as the default TTS.
9. enter the setup Ivona TTS / install voice data / select the folder you created in step в„–0 (ie, / sdcard / ivona /, rather than /sdcard/ivona/rus.rus.tatyana/) / press the OK / Check log / click Close
A return to the main screen (home)
B. Enter the setting again Ivona TTS / Language / Select a voice. If the list is blank votes - restart TTS (or Android, it's easier)
C. go back / click on "Listen to an example", it should work
* TTS to reboot, you can simply rotate the screen (landscape orientation change<->portrait) while in settings Text-To-Speech.
1. Download rus.rus.tatyana. *. Rar
2. extract it to the folder you created in step в„–0
3. Make sure that you have the following 4 files in /sdcard/ivona/rus.rus.tatyana/
lang_ru_ru.dat
libttsivonavoice.so
libvoice_ru_tatyana.so
vox_ru_tatyana22i
4. copy the filelang_ru_ru.dattwice
lang_ru_ru.dat ->lang_ru_ru_tatyana .dat
lang_ru_ru.dat ->voice_ru_ru_tatyana .dat
5. to taste add the lexicon (s) regular expressions * .lex (russian.lex) and PLS lexicon (s) * .pls (russian.pls)
6. if you need other voices repeat the steps to 1..5
7. Set IvonaTTS.apk
8. enter the setup Text-To-Speech, select "Ivona TTS" as the default TTS.
9. enter the setup Ivona TTS / install voice data / select the folder you created in step в„–0 (ie, / sdcard / ivona /, rather than /sdcard/ivona/rus.rus.tatyana/) / press the OK / Check log / click Close
A return to the main screen (home)
B. Enter the setting again Ivona TTS / Language / Select a voice. If the list is blank votes - restart TTS (or Android, it's easier)
C. go back / click on "Listen to an example", it should work
* TTS to reboot, you can simply rotate the screen (landscape orientation change<->portrait) while in settings Text-To-Speech.
Dictionaries
DictionariesfromDamionSleeper
discussed inIVONA Pronunciation Lexicon Helper
Dictionariesshould be in the voice directory (rus.rus.tatyana).
regex* .lex in files (russian.lex),phonetic / orthographicin * .pls (russian.pls).
Dictionaries should be encodedUTF-8 .
lex without necessarily BOM , pls and work with BOM and without it.
Errors in dictionaries visibleOnly in the log .
discussed inIVONA Pronunciation Lexicon Helper
Dictionariesshould be in the voice directory (rus.rus.tatyana).
regex* .lex in files (russian.lex),phonetic / orthographicin * .pls (russian.pls).
Dictionaries should be encodedUTF-8 .
lex without necessarily BOM , pls and work with BOM and without it.
Errors in dictionaries visibleOnly in the log .
Pictures
Same as for Nuance Vocalizer
If TTS is not running, and there is a desire to understand
PM me logcat log :
1. With filter ITTS
2. At the start of Ivona TTS
1. With filter ITTS
2. At the start of Ivona TTS
LogcatX
 |
 |
log example
V ITTS_TtsService: onCreate ()
V ITTS_TtsService: library = / data / data / ivona.tts / files / dataPath = / storage / emulated / 0 / ivona / logText = 0
V ITTS_ProxyI: Proxy 1.0.0.0a
V ITTS_ProxyI: Data ()
V ITTS_Engine: Engine 1.0.0.0a / library = / data / data / ivona.tts / files / dataPath = / storage / emulated / 0 / ivona / logText = 0
V ITTS_Engine: voice_lib /data/data/ivona.tts/files/
V ITTS_Engine: voice_data / storage / emulated / 0 / ivona /
V ITTS_Engine: addVoice ru-RU Maxim 1.6.30-kindle2 rus.rus.maxim
V ITTS_ProxyI: getAvailableLanguages ​​'rus-RUS-Maxim'
V ITTS_Engine: loadLanguage (rus, RUS, Maxim)
V ITTS_Engine: unloadVoice ()
V ITTS_Engine: Loading voice 'rus.rus.maxim'
V ITTS_Engine: Loading engine library /data/data/ivona.tts/files/rus.rus.maxim/libttsivonavoice.so
V ITTS_Engine: IVONA Text-To-Speech
V ITTS_Engine: ivona-1.6.30-kindle2
V ITTS_Engine: December 2013
V ITTS_Engine: Loading voice 'rus.rus.maxim'
V ITTS_Engine: lib '/data/data/ivona.tts/files/rus.rus.maxim/libvoice_ru_maxim.so'
V ITTS_Engine: vox '/storage/emulated/0/ivona/rus.rus.maxim/vox_ru_maxim22i'
E ITTS_Engine: input_type 'text / plain'
E ITTS_Engine: encoding 'UTF-8'
V ITTS_Engine: setProperty (volume, 62)
V ITTS_ProxyI: loadLanguage (rus, RUS, Maxim) = 2
V ITTS_TtsService: onLoadLanguage (rus, RUS, Maxim) = 2
V ITTS_Engine: setProperty (volume, 62)
V ITTS_ProxyI: isLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_TtsService: onIsLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_ProxyI: isLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_TtsService: onIsLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_ProxyI: isLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_TtsService: onIsLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_TtsService: onSynthesizeText ()
V ITTS_Engine: loadLanguage (rus, RUS, Maxim)
V ITTS_ProxyI: loadLanguage (rus, RUS, Maxim) = 2
V ITTS_TtsService: onLoadLanguage (rus, RUS, Maxim) = 2
V ITTS_Engine: setProperty (rate, 100)
V ITTS_Engine: set: dur_stretch 62
V ITTS_TtsService: onDestroy ()
V ITTS_ProxyI: ~ Data ()
V ITTS_Engine: ~ Engine ()
V ITTS_Engine: unloadVoice ()
V ITTS_TtsService: library = / data / data / ivona.tts / files / dataPath = / storage / emulated / 0 / ivona / logText = 0
V ITTS_ProxyI: Proxy 1.0.0.0a
V ITTS_ProxyI: Data ()
V ITTS_Engine: Engine 1.0.0.0a / library = / data / data / ivona.tts / files / dataPath = / storage / emulated / 0 / ivona / logText = 0
V ITTS_Engine: voice_lib /data/data/ivona.tts/files/
V ITTS_Engine: voice_data / storage / emulated / 0 / ivona /
V ITTS_Engine: addVoice ru-RU Maxim 1.6.30-kindle2 rus.rus.maxim
V ITTS_ProxyI: getAvailableLanguages ​​'rus-RUS-Maxim'
V ITTS_Engine: loadLanguage (rus, RUS, Maxim)
V ITTS_Engine: unloadVoice ()
V ITTS_Engine: Loading voice 'rus.rus.maxim'
V ITTS_Engine: Loading engine library /data/data/ivona.tts/files/rus.rus.maxim/libttsivonavoice.so
V ITTS_Engine: IVONA Text-To-Speech
V ITTS_Engine: ivona-1.6.30-kindle2
V ITTS_Engine: December 2013
V ITTS_Engine: Loading voice 'rus.rus.maxim'
V ITTS_Engine: lib '/data/data/ivona.tts/files/rus.rus.maxim/libvoice_ru_maxim.so'
V ITTS_Engine: vox '/storage/emulated/0/ivona/rus.rus.maxim/vox_ru_maxim22i'
E ITTS_Engine: input_type 'text / plain'
E ITTS_Engine: encoding 'UTF-8'
V ITTS_Engine: setProperty (volume, 62)
V ITTS_ProxyI: loadLanguage (rus, RUS, Maxim) = 2
V ITTS_TtsService: onLoadLanguage (rus, RUS, Maxim) = 2
V ITTS_Engine: setProperty (volume, 62)
V ITTS_ProxyI: isLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_TtsService: onIsLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_ProxyI: isLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_TtsService: onIsLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_ProxyI: isLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_TtsService: onIsLanguageAvailable (rus, RUS, Maxim) = 2
V ITTS_TtsService: onSynthesizeText ()
V ITTS_Engine: loadLanguage (rus, RUS, Maxim)
V ITTS_ProxyI: loadLanguage (rus, RUS, Maxim) = 2
V ITTS_TtsService: onLoadLanguage (rus, RUS, Maxim) = 2
V ITTS_Engine: setProperty (rate, 100)
V ITTS_Engine: set: dur_stretch 62
V ITTS_TtsService: onDestroy ()
V ITTS_ProxyI: ~ Data ()
V ITTS_Engine: ~ Engine ()
V ITTS_Engine: unloadVoice ()
Attached files
ivona.tts_1.0.0.0a8.zip(80.88 Kb)lexicon_examples.zip(1.4 KB)ivona.tts_1.0.0.0a8a.zip(80.84 Kb)ivona.tts_1.0.0.0b.zip(71.79 KB)ivona.tts_1.0.0.0b1.zip(71.64 KB)Post has been editedapokrifX - 23.07.17, 23:17
Alenka @ 26.11.2012, 04:57
Several times reread hat trying to figure out what you can get her to pronounce the names of the callers (1), and in general whether it "beg" to control the phone through voice commands (2) or dial where either the text (3) without being connected to Internet (as does Google synthesizer )? Or is it a completely different programs that have nothing to do with SVOX?
Ochchchen would like to see a detailed answer, or at least to be sent to the topic where you can get such advice ..
Ochchchen would like to see a detailed answer, or at least to be sent to the topic where you can get such advice ..
1. They discussed several times in this thread.
2 and 3. SVOX is only a TTS (Text-to-speech), but you nuzhet Speech-to-Text.
Dragon Go!exactly it should do (as well as on a PC)
Attached files
milena_premium-high_1-0-1.part1.rar(120 MB)milena_premium-high_1-0-1.part2.rar(120 MB)milena_premium-high_1-0-1.part3.rar(120 MB)milena_premium-high_1-0-1.part4.rar(100.74 MB)katya_22_premium-high_1-0-1.part1.rar(120 MB)katya_22_premium-high_1-0-1.part2.rar(120 MB)katya_22_premium-high_1-0-1.part3.rar(37.79 MB)yuri_22_premium-high_1-0-1.part1.rar(120 MB)yuri_22_premium-high_1-0-1.part2.rar(18.9 MB)Vocalizer В© Nuancevoices
* Does not work with VocalizerExpressiveВ© Nuance
Post has been editedapokrifX - 17.06.14, 06:04
* Does not work with VocalizerExpressiveВ© Nuance
Voice models
Compact * Bet2 *
Standard * Dri40_155mrf22 *
Standard-High * Dri40_vssq5f22 *
Plus / Premium-Light * Dri80_1175mrf22 *
Premium * Full_155mrf22 *
Premium-High * Full_vssq5_f22 *
Standard * Dri40_155mrf22 *
Standard-High * Dri40_vssq5f22 *
Plus / Premium-Light * Dri80_1175mrf22 *
Premium * Full_155mrf22 *
Premium-High * Full_vssq5_f22 *
Vote
Nuance Vocalizer voices
With CLC
Premium and Premium-High1 & 2
Without CLC
Premium-LightTomTom 1.0
Standard-HighKobaSpeech 2
Compact, Standard, Standard-High, Premium and Premium-HighEvilShrike
Vocalizer Voices with CLC (install or unpackUniversal extractor)* Default Folder/ Sdcard / Vocalizer /
**voices forVocalizer expressive not suitable, it is necessary to Vocalizer
With CLC
Premium and Premium-High1 & 2
Without CLC
Premium-LightTomTom 1.0
Standard-HighKobaSpeech 2
Compact, Standard, Standard-High, Premium and Premium-HighEvilShrike
Vocalizer Voices with CLC (install or unpackUniversal extractor)
MSI Unpacking
Create the folder C: \ TTS
Copy itVocalizerExpressive-1.0.19.101-rur-Milena-Premium-enu.msi downloaded from freedomscientific
Run the console (cmd.exe )Copy the folderC: \ TTS \ OUT \ Freedom Scientific \ Shared \ VocalizerExpressive \ 1.1 \ languages to SD-card in the Android folder Vocalizer
Copy itVocalizerExpressive-1.0.19.101-rur-Milena-Premium-enu.msi downloaded from freedomscientific
Run the console (cmd.exe )
cd C: \ TTS
msiexec / a VocalizerExpressive-1.0.19.101-rur-Milena-Premium-enu.msi TARGETDIR = C: \ TTS \ OUT / qn / l * v extract.log
msiexec / a VocalizerExpressive-1.0.19.101-rur-Milena-Premium-enu.msi TARGETDIR = C: \ TTS \ OUT / qn / l * v extract.log
Voice from MacOS
You can take the voice of the MacOS: 10.8 - Vocalizer, 10.9 - Vocalizer Expressive
Unpack the archive /System/Library/Speech/Voices/VoiceName.SpeechVoice/Contents/Resources/PCMWave
The file names are encryptedrot13You need to rename before use on Win / Android
Unpack the archive /System/Library/Speech/Voices/VoiceName.SpeechVoice/Contents/Resources/PCMWave
The file names are encryptedrot13You need to rename before use on Win / Android
**voices forVocalizer expressive not suitable, it is necessary to Vocalizer
Post has been editedapokrifX - 17.06.14, 06:04
Vocalizer Expressive 2 В© Nuance voices
common-compact.rar(1.08 MB)
common-high.rar(1.11 MB)
embedded-compact.rar(66.46 MB)
milena_premium-high_1-0-1.part1.rar(120 MB)
milena_premium-high_1-0-1.part2.rar(120 MB)
milena_premium-high_1-0-1.part3.rar(120 MB)
milena_premium-high_1-0-1.part4.rar(100.7 MB)
katya_premium-high_1-0-1.part1.rar(120 MB)
katya_premium-high_1-0-1.part2.rar(120 MB)
katya_premium-high_1-0-1.part3.rar(37.79 MB)
yuri_premium-high_1-0-1.part1.rar(120 MB)
yuri_premium-high_1-0-1.part2.rar(18.93 MB)
milena_embedded-high_1-0-1.part1.rar(120 MB)
milena_embedded-high_1-0-1.part2.rar(29.55 MB)
katya_embedded-high_1-0-1.rar(92.24 MB)
yuri_embedded-high_1-0-1.rar(46,98 MB)
vocalizer_e2.tts_1.0.2.3t2.zip(1.61 MB)
ava_premium-high_1-0-1.part1.rar(120 MB)
ava_premium-high_1-0-1.part2.rar(120 MB)
ava_premium-high_1-0-1.part3.rar(120 MB)
ava_premium-high_1-0-1.part4.rar(104.17 MB)
nathan_premium-high_1-0-0.part1.rar(120 MB)
nathan_premium-high_1-0-0.part2.rar(120 MB)
nathan_premium-high_1-0-0.part3.rar(97.29 MB)
nathan_premium-high_1-0-0.part3.rar(97.29 MB)
common-high-2.rar(1.12 MB)
common-high-3.rar(1.14 MB)
vocalizer_e2.tts_1.0.2.3t3.apk.zip(2.7 MB)
common-high-4.rar(1.14 MB)
lesya_embedded-compact_1-0-0.rar(2.56 MB)
lesya_embedded-pro_1-0-0.rar(47.54 MB)
milena_embedded-compact_1-0-1.rar(6.79 MB)
milena_embedded-pro_1-0-1.rar(54.13 MB)
milena_embedded-high_1-0-1.part1.rar(120 MB)
milena_embedded-high_1-0-1.part2.rar(29.55 MB)
katya-ml_embedded-high_2-0-2.part1.rar(120 MB)
katya-ml_embedded-high_2-0-2.part2.rar(16.1 MB)
Post has been editedapokrifX - 05.12.16, 07:20
Voice models
embedded-compact (Compact / * bet *)
embedded-pro (Plus / * dri80 *)
embedded-high (Premium / * full_155 *)
premium-high (Premium-High / * full_vssq5 *)
embedded-pro (Plus / * dri80 *)
embedded-high (Premium / * full_155 *)
premium-high (Premium-High / * full_vssq5 *)
Alternative locations
Vocalizer Expressive 2 voices availableThen install or extract usingUniversal extractor
Another way to unpack MSI
Create the folder C: \ TTS
Copy itVocalizerExpressive-2.2.121-rur-Milena-PremiumHigh-enu.msi downloaded from freedomscientific
Run the console (cmd.exe )Copy the folderC: \ TTS \ OUT \ Freedom Scientific \ Shared \ VocalizerExpressive \ 2.2 \ languages to SD-card in the Android folder VocalizerEx2
Copy itVocalizerExpressive-2.2.121-rur-Milena-PremiumHigh-enu.msi downloaded from freedomscientific
Run the console (cmd.exe )
cd C: \ TTS
msiexec / a VocalizerExpressive-2.2.121-rur-Milena-PremiumHigh-enu.msi TARGETDIR = C: \ TTS \ OUT / qn / l * v extract.log
msiexec / a VocalizerExpressive-2.2.121-rur-Milena-PremiumHigh-enu.msi TARGETDIR = C: \ TTS \ OUT / qn / l * v extract.log
previous versions
Attached files
common-compact.rar(1.08 MB)common-high.rar(1.11 MB)embedded-compact.rar(66.46 MB)milena_premium-high_1-0-1.part1.rar(120 MB)milena_premium-high_1-0-1.part2.rar(120 MB)milena_premium-high_1-0-1.part3.rar(120 MB)milena_premium-high_1-0-1.part4.rar(100.7 MB)katya_premium-high_1-0-1.part1.rar(120 MB)katya_premium-high_1-0-1.part2.rar(120 MB)katya_premium-high_1-0-1.part3.rar(37.79 MB)yuri_premium-high_1-0-1.part1.rar(120 MB)yuri_premium-high_1-0-1.part2.rar(18.93 MB)milena_embedded-high_1-0-1.part1.rar(120 MB)milena_embedded-high_1-0-1.part2.rar(29.55 MB)katya_embedded-high_1-0-1.rar(92.24 MB)yuri_embedded-high_1-0-1.rar(46,98 MB)vocalizer_e2.tts_1.0.2.3t2.zip(1.61 MB)ava_premium-high_1-0-1.part1.rar(120 MB)ava_premium-high_1-0-1.part2.rar(120 MB)ava_premium-high_1-0-1.part3.rar(120 MB)ava_premium-high_1-0-1.part4.rar(104.17 MB)nathan_premium-high_1-0-0.part1.rar(120 MB)nathan_premium-high_1-0-0.part2.rar(120 MB)nathan_premium-high_1-0-0.part3.rar(97.29 MB)nathan_premium-high_1-0-0.part3.rar(97.29 MB)common-high-2.rar(1.12 MB)common-high-3.rar(1.14 MB)vocalizer_e2.tts_1.0.2.3t3.apk.zip(2.7 MB)common-high-4.rar(1.14 MB)lesya_embedded-compact_1-0-0.rar(2.56 MB)lesya_embedded-pro_1-0-0.rar(47.54 MB)milena_embedded-compact_1-0-1.rar(6.79 MB)milena_embedded-pro_1-0-1.rar(54.13 MB)milena_embedded-high_1-0-1.part1.rar(120 MB)milena_embedded-high_1-0-1.part2.rar(29.55 MB)katya-ml_embedded-high_2-0-2.part1.rar(120 MB)katya-ml_embedded-high_2-0-2.part2.rar(16.1 MB)Post has been editedapokrifX - 05.12.16, 07:20
Ivona TTS 21+
ivona.tts_1.0.0.0c.zip(64.82 Kb)
Post has been editedapokrifX - 19.11.17, 09:48
How to
Rewrote all application internals to comply with API Level: 21. Android 5.0 (LOLLIPOP) and above.
Most settings are similar to ICS + version.
Default voices folder: / sdcard / Ivona
* To use external sdcard follow instructions on fixing sdcard permissions for your Android device.
Need to use voices with same version. Current version is 1.6.101.3 (April 2017)
Voices will not work without lex and pls dictionaries.
Need sdcard read permission to load voices.
Can install voices from Ivona TTS settings menu, top level "install voices" is disabled on some Androids.Voices
Most settings are similar to ICS + version.
Default voices folder: / sdcard / Ivona
* To use external sdcard follow instructions on fixing sdcard permissions for your Android device.
Need to use voices with same version. Current version is 1.6.101.3 (April 2017)
Voices will not work without lex and pls dictionaries.
Need sdcard read permission to load voices.
Can install voices from Ivona TTS settings menu, top level "install voices" is disabled on some Androids.
logcat logging
Logs are written to /sdcard/Android/data/ivona.tts/files folder.
It's the only folder where TTS is allowed to write to sdcard
Do not enable it unless you need to do troubleshooting.
It's the only folder where TTS is allowed to write to sdcard
Do not enable it unless you need to do troubleshooting.
Partial voices
If you have four voices available eng.gbr.amy, eng.gbr.brian, eng.usa.joey, eng.usa.salli, enabling partial voices show three more voices: eng.gbr, eng.usa, eng
You can choose what real voice is used when partial one is selected:
eng.gbr: eng.gbr.amy, eng.gbr.brian
eng.usa: eng.usa.joey, eng.usa.salli
eng: eng.gbr.amy, eng.gbr.brian, eng.usa.joey, eng.usa.salli
TTS shows partial voices in the list only when corresponding checkbox is checked (after TTS restart)
TTS client can use partial voices regardless of checkbox state.
You can choose what real voice is used when partial one is selected:
eng.gbr: eng.gbr.amy, eng.gbr.brian
eng.usa: eng.usa.joey, eng.usa.salli
eng: eng.gbr.amy, eng.gbr.brian, eng.usa.joey, eng.usa.salli
TTS shows partial voices in the list only when corresponding checkbox is checked (after TTS restart)
TTS client can use partial voices regardless of checkbox state.
how
I rewrote all internal applications to meet the level of API: 21. Android 5.0 (LOLLIPOP) and above.
Most of the settings are similar versions of ICS +.
Default folder: / sdcard / Ivona
* To use the external SD-card, follow the instructions to correct the sdcard permissions for your Android-device.
You must use the voices with the same version. Current version 1.6.101.3 (April 2017)
Voices will not work without a dictionary, and lex pls.
It requires permission to read sdcard to download vote.
You can set the voice of the setup menu Ivona TTS, the top level "install voice" is disabled on some androids.
Most of the settings are similar versions of ICS +.
Default folder: / sdcard / Ivona
* To use the external SD-card, follow the instructions to correct the sdcard permissions for your Android-device.
You must use the voices with the same version. Current version 1.6.101.3 (April 2017)
Voices will not work without a dictionary, and lex pls.
It requires permission to read sdcard to download vote.
You can set the voice of the setup menu Ivona TTS, the top level "install voice" is disabled on some androids.
Logging Logcat
Logs are written in /sdcard/Android/data/ivona.tts/files folder.
This is the only folder where TTS allowed to write on SDCard
Do not include it if you do not need to perform troubleshooting.
This is the only folder where TTS allowed to write on SDCard
Do not include it if you do not need to perform troubleshooting.
partial vote
If you have 4 votes, available eng.gbr.amy, eng.gbr.brian, eng.usa.joey, eng.usa.salli, allowing partial voices show 3 more votes: eng.gbr, eng.usa, eng
You can choose which real voice is used when selecting the partial:
eng.gbr: eng.gbr.amy, eng.gbr.brian
eng.usa: eng.usa.joey, eng.usa.salli
eng: eng.gbr.amy, eng.gbr.brian, eng.usa.joey, eng.usa.salli
TTS voices shows partial list only when the corresponding flag is set (after restarting the TTS)
TTS client can use the partial voice regardless of the state of the flag.
You can choose which real voice is used when selecting the partial:
eng.gbr: eng.gbr.amy, eng.gbr.brian
eng.usa: eng.usa.joey, eng.usa.salli
eng: eng.gbr.amy, eng.gbr.brian, eng.usa.joey, eng.usa.salli
TTS voices shows partial list only when the corresponding flag is set (after restarting the TTS)
TTS client can use the partial voice regardless of the state of the flag.
Attached files
ivona.tts_1.0.0.0c.zip(64.82 Kb)Post has been editedapokrifX - 19.11.17, 09:48
sm151058 @ 28.11.2012, 03:10
What is so good Nuance (2nd place)? What are its advantages over the other two? (I have not found, and the lack of any).
sm151058 @ 30.11.2012, 05:54
Both?!! I have 6 units on mobile devices and tens in the big blind. And 12 years of experience in the hearing.
And what do you think, a couple of the best voices for BB and mobile devices.
And, if possible, in a nutshell, is why. : Thank_you:
Alenka @ 26.11.2012, 04:57
Several times reread hat trying to figure out what you can get her to pronounce the names of the callers (1), and in general whether it "beg" to control the phone through voice commands (2) or dial where either the text (3) without being connected to Internet (as does Google synthesizer )? Or is it a completely different programs that have nothing to do with SVOX?
Ochchchen would like to see a detailed answer, or at least to be sent to the topic where you can get such advice ..
Ochchchen would like to see a detailed answer, or at least to be sent to the topic where you can get such advice ..
1. They discussed several times in this thread.
2 and 3. SVOX is only a TTS (Text-to-speech), but you nuzhet Speech-to-Text.
Dragon Go!exactly it should do (as well as on a PC)
barket @ 29.11.2012, 13:04
for Nuance you want installed (nesnesonny out) PikoTTS?
Vinitu2 @ 29.11.2012, 01:16
Another b found a good man and corrected Nuance. So there was no stopping in the text and wacky expressions: the comma, that's what your version .. closing double herringbone and others.
Since the process of improving the infinite in its nature, I advise you to learn and do yourself. ;-)
Vinitu2 @ 30.11.2012, 17:00
Like so I did ...
In Notepad, open a file, added a new line, left retaining result, switch the engine on Google and back, opened the reader clicked reading voice, there is no change.
What did not? Some lines I directly from the theme and copied.
In Notepad, open a file, added a new line, left retaining result, switch the engine on Google and back, opened the reader clicked reading voice, there is no change.
What did not? Some lines I directly from the theme and copied.
Attached files
tian-tian-embedded-pro-compact.rar(16.66 MB)Post has been editedapokrifX - 17.11.17, 09:08
apokrifX @ 01.12.2012, 05:44
This is only half the battle. I gave an example of how to check and replace the search string. What line are you checking?
I have a general reading room all react differently to Nuance. Rather engine responds differently to the fact that it is preparing to read a program-reader. Svox behaved the same in all.
Please do not send me back to learn to check regesy. I do not see the point, because of the lack of reaction of the engine to these actions. Maybe even what options are there?
And yet at Nuance. Here are two sentences from the text:
- Wow, my little one - with a laugh forced himself Mr. Dursley, leaving home.
- And prividitsya same! - I growled Mr. Dursley.
While reading the first Nuance in MoonReder instead - (hyphen) says "comma".
When reading the second fine.
If anyone noticed that in the first sentence hyphens different from that in the second - they are different (longer). This is the whole and byaka. These long dashes, and Nuance reads in prog MoonReder, as a "comma"!
Unfortunately, in most of my books hyphens it is such (it is clear that the book is not bought and downloaded from the network and who does not find this) and it is necessary to edit the files.
EReader FBreder these hyphens swallow normally, but there is another drawback - stop at *** and they enrage greatly.
For users of Nuance: I found a bunch of books for normal listening. It MoonReader Pro + Nuance + Management Board txt file.
The Board is very simple: open the file in Word and save as plain txt, while maintaining put checkbox on the "Allow Wildcards". At the same time "curves" are replaced with the standard. Now, the engine stops talking in the reader "comma" and you can listen to normal.
Post has been editedapokrifX - 24.03.13, 16:59
Vocalizer Express Studio
Official editor of dictionaries at the PC from the Nuance
Official editor of dictionaries at the PC from the Nuance
 |
Instructions Vocalizer Express Studio launch in English
0. Main folder [Nuance]
x86 =>C: \ Program Files \ Nuance
x64 =>C: \ Program Files (x86) \ Nuance
Directory of C: \ Program Files (x86) \ Nuance
<DIR>Vocalizer expressive
<DIR>Vocalizer Expressive Studio
1. Unpack "\ Vocalizer Expressive Studio 1" from VEStudio.zip to
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive Studio
<DIR>clc
<DIR>doc
<DIR>license_agreements
<DIR>studio
2. Unpack "\ common \ speech \ components" from ve_engine_v1.4.0_win32.zip
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ components
2829260 clm.dat
46 input.txt
1153748 lid.dat
21412 synth_med_fxd_bet3f22.dat
103,576 sysdct.dat
2703360 ve.dll
335872 vedemo.exe
44544 ve_cdfinit.dll
2682880 ve_sapi5.dll
110592 ve_toolsapi.dll
3. Place Vocalizer Expressive language to "C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ languages". For Milena it'll be:
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ languages ​​\ rur \ speech
<DIR>components
<DIR>ve
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ languages ​​\ rur \ speech \ components
2314391 clc_rur_cfg3.dat
58125 clc_rur_milena_cfg3.dat
58225 clc_rur_yuri_cfg3.dat
480,200 select_milena_bet3f22.dat
479,476 select_yuri_bet3f22.dat
38705256 synth_milena_dri80_1175mrf22_1175_02.dat
2571060 synth_milena_dri80_1175mrf22_1175_02_pmk.dat
446681420 synth_milena_full_vssq5_f22.dat
13160584 synth_milena_full_vssq5_f22_pmk.dat
3926992 uselect_milena_dri80.dat
17507204 uselect_milena_full.dat
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ languages ​​\ rur \ speech \ ve
2700 ve_pipeline_rur_milena_22_bet3.hdr
2832 ve_pipeline_rur_milena_22_dri80_1175mrf22.hdr
2820 ve_pipeline_rur_milena_22_full_vssq5f22.hdr
2690 ve_pipeline_rur_yuri_22_bet3.hdr
4. Run "C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive Studio \ studio \ VocalizerExpressiveStudio.exe"
5. Setup | Add | "C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \" | Ok
x86 =>C: \ Program Files \ Nuance
x64 =>C: \ Program Files (x86) \ Nuance
Directory of C: \ Program Files (x86) \ Nuance
<DIR>Vocalizer expressive
<DIR>Vocalizer Expressive Studio
1. Unpack "\ Vocalizer Expressive Studio 1" from VEStudio.zip to
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive Studio
<DIR>clc
<DIR>doc
<DIR>license_agreements
<DIR>studio
2. Unpack "\ common \ speech \ components" from ve_engine_v1.4.0_win32.zip
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ components
2829260 clm.dat
46 input.txt
1153748 lid.dat
21412 synth_med_fxd_bet3f22.dat
103,576 sysdct.dat
2703360 ve.dll
335872 vedemo.exe
44544 ve_cdfinit.dll
2682880 ve_sapi5.dll
110592 ve_toolsapi.dll
3. Place Vocalizer Expressive language to "C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ languages". For Milena it'll be:
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ languages ​​\ rur \ speech
<DIR>components
<DIR>ve
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ languages ​​\ rur \ speech \ components
2314391 clc_rur_cfg3.dat
58125 clc_rur_milena_cfg3.dat
58225 clc_rur_yuri_cfg3.dat
480,200 select_milena_bet3f22.dat
479,476 select_yuri_bet3f22.dat
38705256 synth_milena_dri80_1175mrf22_1175_02.dat
2571060 synth_milena_dri80_1175mrf22_1175_02_pmk.dat
446681420 synth_milena_full_vssq5_f22.dat
13160584 synth_milena_full_vssq5_f22_pmk.dat
3926992 uselect_milena_dri80.dat
17507204 uselect_milena_full.dat
Directory of C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \ common \ speech \ languages ​​\ rur \ speech \ ve
2700 ve_pipeline_rur_milena_22_bet3.hdr
2832 ve_pipeline_rur_milena_22_dri80_1175mrf22.hdr
2820 ve_pipeline_rur_milena_22_full_vssq5f22.hdr
2690 ve_pipeline_rur_yuri_22_bet3.hdr
4. Run "C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive Studio \ studio \ VocalizerExpressiveStudio.exe"
5. Setup | Add | "C: \ Program Files (x86) \ Nuance \ Vocalizer Expressive \" | Ok
- simona_rex_ror.zip(358 bytes)
- VEStudio.zip(27.7 MB)
- ve_engine_v1.4.0_win32.zip(8.39 MB)
- ve.dll_1.5.0.15008.zip(1.32 MB)
Vinitu2 @ 01.12.2012, 01:14
Here are two sentences from the text:
- Wow, my little one - with a laugh forced himself Mr. Dursley, leaving home.
- And prividitsya same! - I growled Mr. Dursley.
While reading the first Nuance in MoonReder instead - (hyphen) says "comma". When reading the second fine.
- Wow, my little one - with a laugh forced himself Mr. Dursley, leaving home.
- And prividitsya same! - I growled Mr. Dursley.
While reading the first Nuance in MoonReder instead - (hyphen) says "comma". When reading the second fine.
Vinitu2 @ 01.12.2012, 18:02
Who drew attention, in the first sentence hyphens differ from those in the second. This is the whole and byaka. These long dashes, and Nuance reads in prog MoonReder, as a "comma". Unfortunately, in most of my books hyphens exactly such and need to edit the files.
Try to change
/([\?!])-/ --> "$1"
on
/([\?!])[-пїЅ]/ --> "$1"
Vinitu2 @ 01.12.2012, 18:02
In this Fbreder chitalke not, but it stops at *** enrage greatly.
Post has been editedapokrifX - 02.11.16, 07:03
retigor @ 02.12.2012, 12:06
It's about "ragged" Loquendo TTS pronunciation to Wildfirer_S.
The problem is not does not depend on the selected voice Loquendo (Olga and Dmitry), not from the selected reading room (Cool_Reader, Moon_Reader, FBReader (c each of the two plug-ins). The defect of speech constantly repeated in the same places and crouches usually a comma, but not each, either dots or even just between words, and the dependence of such a defect (from the combination of letters) I do not understand is found such a defect about a proposal of three -.. four, and in the same sentence can be repeated several times is also a defect does not depend on frequency and pronunciation speed.
The problem is not does not depend on the selected voice Loquendo (Olga and Dmitry), not from the selected reading room (Cool_Reader, Moon_Reader, FBReader (c each of the two plug-ins). The defect of speech constantly repeated in the same places and crouches usually a comma, but not each, either dots or even just between words, and the dependence of such a defect (from the combination of letters) I do not understand is found such a defect about a proposal of three -.. four, and in the same sentence can be repeated several times is also a defect does not depend on frequency and pronunciation speed.
On hearing this defect, I would compare with switching noise, ie, very brief, but biting and clear click, similar to the switching connection connection.
I thought that at the time of the pause resets the processor frequency, and then when it increases, there is this nonsense. But check CPU usage, so the engine Loquendo TTS is more than 10% does not load, ie, with all the twists processor loaded with a maximum (peak load) of not more than 25%.
Thought that perhaps the text formatting characters can provoke that, but no, * .txt texts the same.
Perhaps I dumoyu that the defect can be associated with changes in voice parameters at the time of pause when reading, but that this can provoke, is unclear. So, to stop a whole slew of background programs, zero effect.
I thought that at the time of the pause resets the processor frequency, and then when it increases, there is this nonsense. But check CPU usage, so the engine Loquendo TTS is more than 10% does not load, ie, with all the twists processor loaded with a maximum (peak load) of not more than 25%.
Thought that perhaps the text formatting characters can provoke that, but no, * .txt texts the same.
Perhaps I dumoyu that the defect can be associated with changes in voice parameters at the time of pause when reading, but that this can provoke, is unclear. So, to stop a whole slew of background programs, zero effect.
Let's try to repeat on the other androids and we will decide what to do next. Not the fact that you can do to fix ...
Still I do not know should be - whether it is to be, or not, but not in the same application to change the speed of reading, I can not (any votes, and not only Loquendo). So, the speed of reading, I can only change in the Android settings.
sm151058 @ 02.12.2012, 03:20
I moon sometimes stops at the end of the chapter. How to deal with it?
Vinitu2 @ 02.12.2012, 03:23
In vain do not believe. I spent a lot of time and thought to myself the problem. Thanks for the help. A dozen files corrected on the computer for a few minutes for a month enough.
Post has been editedapokrifX - 27.10.16, 19:37
saniab @ 14.12.2012, 05:10
apokrifX @ 02.12.2012, 07:24
saniab @ 13.12.2012, 14:59
Nuance on the Moon speaks comma at the beginning of the paragraph before the long dash. I have tried to rule like this was proposed, but to no avail. Can someone tell, help?
Post has been editedapokrifX - 10.10.13, 07:24
saniab @ 14.12.2012, 12:02
apokrifX @ 14.12.2012, 18:49
That's right, onlyrex_rur.dat not reread after editing - the easiest way to reload Android.
# Fix TT-Latin problems (needed for every language except Czech, Slovak and Lakota)
/ E- / -> "t '"
/ A_ / -> "d '"
/ A_ / -> "l '"
/ E- / -> "t '"
/ A_ / -> "d '"
/ A_ / -> "l '"
Post has been editedapokrifX - 10.10.13, 07:27
saniab @ 14.12.2012, 17:11
It seems to me that do not work. Although I could be wrong. But bore no result rows returned.
apokrifX @ 14.10.2012, 18:38
Added 2 Milena (Voice Data)
Milena-Premium - milena_22_full_155mrf22 - 143,913,679 bytes
Milena-Premium-High milena_full_vssq5_f22 - 480,284,734 bytes
Checked at - well, very much the quality of the pronunciation is different ... and size too.
Milena-Premium - milena_22_full_155mrf22 - 143,913,679 bytes
Milena-Premium-High milena_full_vssq5_f22 - 480,284,734 bytes
Checked at - well, very much the quality of the pronunciation is different ... and size too.
PM if anyone should, and can reload Samantha Samantha, Premium and Premium-High.
saniab @ 21.12.2012, 16:12
Nuance 1.1 Voice like a better place, but the comma says continue.
Post has been editedapokrifX - 01.07.13, 02:13
©savagemessiahzine.com2005-2020 All rights reserved.
savagemessiahzine.com®- registered trademark.
Terms of Use | Denial of responsibility | Advertising placement
savagemessiahzine.com®- registered trademark.
Terms of Use | Denial of responsibility | Advertising placement