-
Notifications
You must be signed in to change notification settings - Fork 224
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
German Voice for RHVoice #24
Comments
Training data: text, audio files that read that text, and mapping that maps audio to the text. |
If I understand you right, you need a nativ speaker who reads a text an And what you mean with:
You need the spoken text as a text file? What criteria should have the read text? Is it necessary that this text is recorded in a studio or could it be Sorry for the beginner questions, but I am a beginner in this aria |
Yes.
Yes.
That depends on a language. Basically the text should be chosen in a way that audio for it contains all possible combinations of sounds, or at least cover most popular.
It is better to record in studio with highest quality, because then you can convert audio to different formats. But.. it is possible to record with headset too. Mind you that software is dumb - it doesn't know where words starts in your audio, so you will have to mark audio files with text manually ( |
OK, now I am closer to understand you. :)
How can I do this? I am a blind person. If I give you a spoken text and If it is too difficult to create a German Voice Database, we need |
@winman3000 how do you use RHVoice primarily? Maybe there is already a voice for your platform or there might be available training bases. I think that any training material for HTS-type synthesizer will do. And answering your question, me personally is unlikely to create the voice, because this project is not funded and I am afraid there is still a lot of missing bits to fill in that take time. But if we get training data, it is at least possible to see what is next. |
how do you use RHVoice primarily?
Currently I don't use RHVoice as it is not in German, but I've tested
the English ones with NVDA. If a German Voice would be available in the
future, I'll use this Voice.
Maybe there is already a voice for your platform or there might be
available training bases.
There should be training bases, as MaryTTS is using HTS based voices and
MaryTTS has German voices. But I am not able to find the training data.
If I could find the training data, it would be easier to find the next
steps I think. As far as I know, the German voices are publiced as a BSD
license, so I'm afraid that we cannot use these voices. It would be nice
to have the training materials.
|
Yes, MaryTTS is what I thought of too. They also provide a nice diagram of
the whole process, but details are still a bit elusive. Guys are also very
responsive. So we should ask them. I think it is also possible to hire
Olga, but I don't have contact with her.
BSD license is not a problem. It is not hard to give proper credit in voice
documentation. But we need better docs - targeted at simple users who are
not linguists or mathematicians, but who want to hack on voice
technologies. And I personally think that blind users should take the lead
and explain to everybody else how it works and what should we do. =)
|
Have you an idea how to contact the developers of Mary TTS? I know there
are in GitHub, but I don't know the way to contact the team leaders. The
only thing I can do is only open a ticket.
|
It's better to give a link to marytts/marytts#440 You can also contact marytts developers on the mailing list http://www.dfki.de/mailman/cgi-bin/listinfo/mary-users Voice building for rhvoice is not trivial, you could probably better just use nvda plugin for openmary with openmary voices. Openmary also has better synthesis quality due to mixed excitation vocoder and advanced NLP components. |
I've got a link from a developer or so for German. Can you work with it?
http://www.voxforge.org/de/Downloads
|
The bad thing in MaryTTS is that the responsiveness is not fast as in RH
Voice. The second thing is that you need Java.
|
As for Voxforge files, I need to check if audio files are annotated, and if
RHVoice training pipeline can handle this format.
|
Right. RHVoice is optimized for responsiveness. But I don't understand why
building voice for RHVoice should be harder than for any other HTS
synthesizer. For now the main problem is the lack of complete picture.
|
As far as I know, these files are annotated.
It would be very great when you can check this. Thank you very much for your help! |
Some analysis.
I am not really sure what this label means |
Okay. http://www.repository.voxforge1.org/downloads/de/Trunk/Audio/Original/48kHz_16bit/ contains |
Hmm. So we cannot build a voice for RHVoice with this stuff? ralfherzog
is the name, but I don't know the rest. After this it is the sentence.
|
I would not be that pessimistic and try well documented openmary voice import procedure first. |
@abitrolly latest wiki is on github: https://github.com/marytts/marytts/wiki/VoiceImportToolsTutorial that one on opendfki might be slightly outdated. |
@nshmyrev thanks. Just need to get some free time now. |
Why not just use Common Voice? |
@rugk Hello! I'm not sure about the German dataset, but russian dataset include a lot of different dictors. |
hello.
common voice as i know is targetted for creation of rnn voices.
the way they're built is a bit different. this method doesn't
specifically need one voice as it builds acoustic model. but for
rhvoice it is a requirement of good quality recording of one speaker
to create a voice as technologies are different.
…On 10/17/20, Artem Plaksin ***@***.***> wrote:
@rugk Hello!
Sorry, but it's very bad quality.
Besides the text is missing in dataset.
I'm not sure about the German dataset, but russian dataset include a lot of
different dictors.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
#24 (comment)
--
with best regards beqa
|
Ah okay, thanks, this makes sense. Of course, yeah, their idea, was to collect many voices… |
Is there any progress on this in the meantime? Has anyone tried to import the voices from MaryTTS for RHVoice? If there is no existing data we can use for this project, we will have to do everything from scratch. Unfortunately I have to repeat my questions:
I would love to finish the project so that we finally have a German voice as well... |
I have found some voices including German, I use them with VocalizerEx2 TTS. They are working fine, but I do not trust VocalizerEx2. Would be nice to have these voices in RHVoice (: |
Not really! It will be the infringement of copyright, and it is not possible, because of the synthesis method.
From: citizenserious ***@***.***>
Sent: Tuesday, December 7, 2021 7:46 PM
To: RHVoice/RHVoice ***@***.***>
Cc: Subscribed ***@***.***>
Subject: Re: [RHVoice/RHVoice] German Voice for RHVoice (#24)
I have found some voices including German, I use them with VocalizerEx2 TTS. They are working fine, but I do not trust VocalizerEx2. Would be nice to have these voices in RHVoice (:
https://vocalizer-nvda.com/downloads
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub <#24 (comment)> , or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACVCDE4DLTITFBTH6ZBDTY3UPZI7TANCNFSM4BWG54KA> .
Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub> . <https://github.com/notifications/beacon/ACVCDE3FWPFE55BT7KTHKSDUPZI7TA5CNFSM4BWG54KKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOHLTG4DI.gif>
|
Any progress? |
As far as I know, there is no progress on this. Apparently it is not enough to make language recordings, modules must also be adapted in C++, i.e. libraries must be developed for the German language. |
You need to ask Torsten https://github.com/thorstenMueller/Thorsten-Voice, he will make the voice for you. |
Maybe we should contact Torsten Müller and ask if he would be willing to port his voice for RHVoice. We will definitely need someone to write the modules for German in C++. Unfortunately I do not have programming skills myself. |
Hi,
You don’t need to write anything in c++.
Please see, for example, the polish language as an example.
You can create the data only language, which is imported by RHVoice without knowing it by the engine.
You need to learn how foma language regexes work.
There are tutorials and regex references available.
From: winman3000 ***@***.***>
Sent: Monday, August 15, 2022 7:02 PM
To: RHVoice/RHVoice ***@***.***>
Cc: Zvonimir Stanečić ***@***.***>; Comment ***@***.***>
Subject: Re: [RHVoice/RHVoice] German Voice for RHVoice (#24)
Maybe we should contact Torsten Müller and ask if he would be willing to port his voice for RHVoice. We will definitely need someone to write the modules for German in C++. Unfortunately I do not have programming skills myself.
—
Reply to this email directly, view it on GitHub <#24 (comment)> , or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACVCDE3JV3XG3NOT3YNHJZTVZIWTXANCNFSM4BWG54KA> .
You are receiving this because you commented. <https://github.com/notifications/beacon/ACVCDE2CG7K6KXRI45I3XT3VZIWTXA5CNFSM4BWG54KKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOJBVGZ7Q.gif> Message ID: ***@***.*** ***@***.***> >
|
Hi and sorry for joing late to discussion. I tried to figure out required steps to add german language based on my Thorsten-Voice dataset. The "Polish" language was referenced but honestly i'm not sure what to do. |
Hi Thorsten,
First of all, you will need to define the language rules in the foma scripting language, then compile these to fst, with the foma compiler and interpreter.
The version which is needed is v 0.9.18.
Newer version causes issues.
Secondly, you will need to create the phonemes features in xml file, as defined for example for polish. For german you will need to modify thinks a bit, or probably from scratch.
Thirdly, you will need to have labelling.xml.
As the language you will create will be data only, you will need the language.conf and graph.tx.. This is for registering the letters and telling the synthesizer which of these are consonants, and which are wovels.
Feel free to ask questions if these will arise.
From: Thorsten Müller ***@***.***>
Sent: Saturday, January 7, 2023 3:19 PM
To: RHVoice/RHVoice ***@***.***>
Cc: Zvonimir Stanečić ***@***.***>; Mention ***@***.***>
Subject: Re: [RHVoice/RHVoice] German Voice for RHVoice (#24)
Hi and sorry for joing late to discussion.
I tried to figure out required steps to add german language based on my Thorsten-Voice dataset. The "Polish" language was referenced but honestly i'm not sure what to do.
@zstanecic <https://github.com/zstanecic> Would you mind helping me with the first steps?
—
Reply to this email directly, view it on GitHub <#24 (comment)> , or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACVCDE2HW6XSYR6OQJPLVITWRF3LZANCNFSM4BWG54KA> .
You are receiving this because you were mentioned. <https://github.com/notifications/beacon/ACVCDE45O46AMV4GVZZTWOTWRF3LZA5CNFSM4BWG54KKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOKHWSLBA.gif> Message ID: ***@***.*** ***@***.***> >
|
Hi @zstanecic , what i did so far:
Am i right, that ...
Once this is done i guess i've to create a "Thorsten" folder in the /data/voices folder? And do whatever way of magic there ;-). |
Hi Thorsten,
That’s not the right way to start.
You need to check the foma scripts first, and write the rules for your language.
Scripts are located in rhvoice/scripts/language.
You will need examples of data only languages.
Let me contact privately on some whatsapp or email to explain this further.
***@***.*** ***@***.***>
From: Thorsten Müller ***@***.***>
Sent: Saturday, March 11, 2023 4:19 PM
To: RHVoice/RHVoice ***@***.***>
Cc: Zvonimir Stanečić ***@***.***>; Mention ***@***.***>
Subject: Re: [RHVoice/RHVoice] German Voice for RHVoice (#24)
Hi @zstanecic <https://github.com/zstanecic> ,
what i did so far:
* Installed foma in version 0.9.18
* Created folder /data/languages/German
* In that "German" folder i've copied the following files from "Polish" directory: graph.txt, labelling.xml, language.conf, language.info, locale.info, phonemes.xml
Am i right, that ...
* i have to adjust all these files (or less or more) to german?
* running "foma" (do not know this tool at all, yet) will create several.fst and dt files?
Once this is done i guess i've to create a "Thorsten" folder in the /data/voices folder? And do whatever way of magic there ;-).
—
Reply to this email directly, view it on GitHub <#24 (comment)> , or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACVCDE6RLCUZN7RQCO7BJKDW3SJWFANCNFSM4BWG54KA> .
You are receiving this because you were mentioned. <https://github.com/notifications/beacon/ACVCDE4SFFKZIKTDZXC7ZFLW3SJWFA5CNFSM4BWG54KKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOK5IRWSQ.gif> Message ID: ***@***.*** ***@***.***> >
|
Thanks for your quick reply and support offer. As i've never worked with foma this is really highly appreciated. |
Hi,
I sent you a msg. please check your inbox
From: Thorsten Müller ***@***.***>
Sent: Saturday, March 11, 2023 4:37 PM
To: RHVoice/RHVoice ***@***.***>
Cc: Zvonimir Stanečić ***@***.***>; Mention ***@***.***>
Subject: Re: [RHVoice/RHVoice] German Voice for RHVoice (#24)
Thanks for your quick reply and support offer. As i've never worked with foma this is really highly appreciated.
Github mail doesn't show your mail please contact me here and we can talk by mail then.
https://www.thorsten-voice.de/en/contact/
—
Reply to this email directly, view it on GitHub <#24 (comment)> , or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACVCDE5BA2BYU4FLSWCTIVTW3SLYFANCNFSM4BWG54KA> .
You are receiving this because you were mentioned. <https://github.com/notifications/beacon/ACVCDEYGRXR5OUVRV5ORCSLW3SLYFA5CNFSM4BWG54KKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOK5ISO7Q.gif> Message ID: ***@***.*** ***@***.***> >
|
Hi,
This basic work has nothing to do with the actual voice, it's more a basic grammar setup and rules for german language. Honestly i cannot work this out all by my self. I'll read So any help on this is appreciate if we'd like to add german / Thorsten-Voice to RHVoice. |
@thorstenMueller thx for your effort. Maybe I can help a bit with adjusting the basic grammar and rules. But I don't know how exactly. |
May this be helpful? |
any news? |
Not from my side yet. Topic is absolutely interesting but remaining free time is (as mostly) is limited. |
What about the Piper voices? |
It would be nice to have RH Voice in German. What do you Need for German language?
The text was updated successfully, but these errors were encountered: