Comments (5)
rsxdalv
commented on May 25, 2024
1
I've seen some implementations of it but I didn't quite like them.
The less in depth it is the easier.
If it's just stopping the multiple generations, it wouldn't be so hard.
Split prompt would be a little harder.
Stopping bark between semantic coarse and fine is harder.
Stopping bark mid-coarse generation is unlikely to be justifiable in terms
of complexity.
What depth are you looking for?
…On Mon, Jul 24, 2023, 1:00 AM MiYaku Gaming ***@***.***> wrote:
When I generate anything, it works perfectly, however, sometimes I am
finding I made a typo, mistake or something else and have to close it out
entirely and come back to it again.
Can there be a halt or stop Generation when Generating Audio Samples?
—
Reply to this email directly, view it on GitHub
<#93>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABTRXI76ZI3YE27TQNZMZUDXRWNITANCNFSM6AAAAAA2UYQOHM>
.
You are receiving this because you are subscribed to this thread.Message
ID: ***@***.***>
from tts-generation-webui.
rsxdalv
commented on May 25, 2024
1
I see, your workflow sounds rather complex. Personally I use an audio
editor alongside the generation UI (like maybe I'll need to fix a mistake,
then I'll combine two generations together 50/50)
As for the seeds - yes they are saved in the history, but I guess you want
a more advanced UI for them. That's an interesting idea! I might make a
separate tool for labelling seeds (it's much more efficient for development
to have it separate). Also different seeds work differently for each npz
file. When I use them, just changing a few words usually changes the whole.
So as for the interrupt button, as long as it stops the long generation
it's fine, right? Not necessarily terminating the generation midway.
…On Mon, Jul 24, 2023, 2:49 AM MiYaku Gaming ***@***.***> wrote:
Well, I do a lot of dialog that has a lot of text for my Translations, so
I have been unchecking split prompt but I do generate 9 Samples to find the
best take and usually out of the 9, 1 is typically the best, and I delete
the bad takes and favorite the good takes.
Sometimes I don't even catch a typo, misspelling or error of some sort
until the Generation has begun, but I have been working on being aware
instead of doing a Generation, but maybe it's just me going quickly and not
noticing it.
Which reminds me, is it possible to have a seed tracker, saver or labeler
of some sort?
I have been saving a text file with seeds and what emotions they evoke.
Favorites are good and all, but you have to click them just to find out
what seed they are, and when there's a lot, it takes too long.
When I have to Generate shorter text or a few words and it's not complex,
I have no problem as I typically find many Generations that go fast and all
are useful.
—
Reply to this email directly, view it on GitHub
<#93 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABTRXIYKHGPTIZC5PQRLFELXRWZ7VANCNFSM6AAAAAA2UYQOHM>
.
You are receiving this because you commented.Message ID:
***@***.***>
from tts-generation-webui.
rsxdalv
commented on May 25, 2024
1
I experienced it today, yes, I need this as well. It's actually not that hard to add it but the code will become convoluted.
from tts-generation-webui.
MiYakuGaming
commented on May 25, 2024
Well, I do a lot of dialog that has a lot of text for my Translations, so I have been unchecking split prompt but I do generate 9 Samples to find the best take and usually out of the 9, 1 is typically the best, and I delete the bad takes and favorite the good takes.
Sometimes I don't even catch a typo, misspelling or error of some sort until the Generation has begun, but I have been working on being aware instead of doing a Generation, but maybe it's just me going quickly and not noticing it.
Which reminds me, is it possible to have a seed tracker, saver or labeler of some sort?
I have been saving a text file with seeds and what emotions they evoke.
Favorites are good and all, but you have to click them just to find out what seed they are, and when there's a lot, it takes too long.
When I have to Generate shorter text or a few words and it's not complex, I have no problem as I typically find many Generations that go fast and all are useful.
from tts-generation-webui.
MiYakuGaming
commented on May 25, 2024
Ah yes, I edit my audio too lol
Yeah, especially during long Generations, but I don't know, I probably just need to ensure I don't have typos and stuff before Generating lol
Well, I was inspired by Automatic1111 given the seed is in the image file and it's a drag and drop situation.
from tts-generation-webui.
Related Issues (20)
- updated today, getting this on start.bat now HOT 3
- How can we change the React UI default port? HOT 3
- Not even sure what's going wrong HOT 8
- Terminal errors when clicking "Generate" HOT 2
- Mp3 option ? HOT 1
- Bark voice clone multiple audio inputs? HOT 1
- Errors when generating-- only with Tortoise HOT 6
- Keeping models in vram all the time HOT 9
- start_linux.sh fails at startup on first install HOT 6
- When trying a fresh install, I get these errors HOT 3
- Check if miniconda is already installed. HOT 5
- Colab installation fails: "Failed to install node_modules" HOT 8
- Can rmvpe be added to pitch collection method in RVC? HOT 4
- Bark Voice Generation error HOT 11
- WebUI does not render properly - compared to images I've seen. And tortoise fails to generate HOT 2
- Not able to generate - tried Bark, Tortoise, and MusicGen HOT 17
- Torch version mixup? HOT 6
- Where is gradio ui HOT 3
- Is it possible to use these facebook/mms-tts models inside tts-generation-webui? HOT 3
- IndexError: index 4 is out of range error when checked Multi-band Diffusion HOT 5
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 tts-generation-webui.