Comments (8)
It's because russian is a dead language not necessary in the modern world.
from alltalk_tts.
Ok.. Give me 10-20 minutes and I should be able to post an update......Ill just need to make a few changes and test...
from alltalk_tts.
Ok, one of two things is going to happen here...
- I've just made a very quick update and its all going to work perfectly and everything will be glorious!
- I've just made a very quick update and broken something as I've not done lots of testing.. 😰
Pretty sure all should be good though. If you want to update with a git pull ... give it a test and it would be good it you can confirm that's fixed things for you (including on the Demo page).
Thanks!
from alltalk_tts.
Ok, one of two things is going to happen here...
- I've just made a very quick update and its all going to work perfectly and everything will be glorious!
- I've just made a very quick update and broken something as I've not done lots of testing.. 😰
Pretty sure all should be good though. If you want to update with a git pull ... give it a test and it would be good it you can confirm that's fixed things for you (including on the Demo page).
Thanks!
Thank you very much. Everything works as before. The only thing. This message pops up in the terminal after starting generation:
[!] "Warning: The text length exceeds the character limit of 182 for language 'ru', this might cause truncated audio."
But still everything worked out as it should. Thanks again for such quick help!
P.S.: Checked it in demo page and on text gen webui
from alltalk_tts.
@Dartvauder Is this within the Text-Generation-WebUI? or the Demo Page? If you put something in the "Preview Text box" does that work?
I guess what Im asking is, just guide me so I could re-create the problem. What would I have to do to make the problem occur?
from alltalk_tts.
@Dartvauder are we talking specifically Cyrillic characters e.g. Рад познакомиться с тобой
from alltalk_tts.
@Dartvauder Is this within the Text-Generation-WebUI? or the Demo Page? If you put something in the "Preview Text box" does that work?
I guess what Im asking is, just guide me so I could re-create the problem. What would I have to do to make the problem occur?
This problem is everywhere. In standalone demo page and in TextGenWebUI. Let's tell you about the actions using a demo page as an example. I run it through cmd_windows.bat - cd extensions - cd alltalk_tts - python script.py. Everything loads normally and quickly. I choose russian language, write cyrillic characters and I press Generate. As a result, I get the following sound at the output:
AI_1704367772.zip
Until I updated the extension everything worked fine. The Cyrillic characters fit into the terminal and at the output I received normal voice acting.
from alltalk_tts.
Yeah, it will warn about anything over 250 characters for English. I didn't know Russian was only 182, probably because of the extra data overhead in the character set. You will always get this warning on longer messages though. However, I did implement text splitting before it actually hits the AI model, which should...... should deal with most issues around that, but you will still get the warning regardless.
As for generating other longer things outside of Text-gen-webui... thats all in the works!
Glad its fixed though! Thanks for letting me know!
from alltalk_tts.
Related Issues (20)
- [GEN] Error during audio generation: 500: Exception while running subprocess: [Errno 2] No such file or directory: 'piper' HOT 1
- problem with Polish language HOT 7
- Standard TTS generation example from the documentation does not work HOT 4
- Need help :( HOT 1
- Support for metavoice-1B HOT 1
- Are you going to add latest Parler TTS large v1 and mini V1 models? HOT 3
- Loading Parlor at 16-bit HOT 1
- Training with ddp doesnt work hangs at init_process_group HOT 1
- Add an option to send a voice (file not name) with the streaming/generation request. HOT 1
- Add ability to request specific audio types HOT 4
- Having narrator enabled in dockerconfig.json results in a silent failure in a clean container HOT 5
- Torch error on text-generation-webui 'Apply requirements' while running at_setup.bat HOT 1
- Different voice for different emotion of character / narrator HOT 5
- API Issues HOT 7
- The "start_alltalk" batch file, but that pops up really briefly and then just disappears again. HOT 2
- AllTalk v2 BETA Download Details & Discussion HOT 4
- ImportError: DLL load failed while importing _imaging: The specified module could not be found. HOT 1
- Connection between SillyTavern & Alltalk works, but Error 500 occured: Model file not found. HOT 3
- DeepSpeed N/A in Gradio Alltalk_v2 HOT 1
- CUDA not detected/python errors when running finetune/diagnostics also throwing error HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from alltalk_tts.