Comments (12)
I've got a very hacky fork that should be pip installable here (still need to create setup.py
), however the training scripts + config files have been removed.
from styletts2.
This repo serves as a research's project, but if it needed surely I can make a pip package. Do you need it for training or for inference?
from styletts2.
Mostly for inference. I was planning to make a Gradio demo, but I can also do that by just cloning the repo. (Might make a PR later if that's ok.)
from styletts2.
Yes, please do so if you can. Thanks for your contribution.
from styletts2.
This will require a restructuring of the files (putting them all in one folder) and may break the demos, so I'll work on it in a fork for now.
from styletts2.
Thanks for this, and the demo, @fakerybakery
Would be nice to have inference.py commited and mainlined.
from styletts2.
Hi @lxe, by inference.py
do you mean a importable script? I'm planning to make a PR to merge the demo + script soon after I clean up the code.
I'm going to delete my pip fork because it breaks training, config, etc. Personally, I think it would be better to have an external "wrapper" repository that's pip-installable to keep the training scripts, similar to how VoiceFixer has the VoiceFixer pip installable package and the VoiceFixer main repository with training scripts, etc.
from styletts2.
@yl4579 would you mind adding this to the "todo" list in the README?
from styletts2.
My main concern of this is it could contain phonemizer and change the license of the repo. I use notebook intentionally so it doesn't contain any non-MIT libraries. Even if I add it to TODO it probably wouldn't be a part of this repo anyway.
from styletts2.
OK, please see the other comment about the fork
from styletts2.
I was able to wrangle around the inability to import this in my own package:
https://github.com/lxe/tts-server
Here's what I needed to do:
- styletts2 is a git submodule
- needed to add this to make some submodules work https://github.com/lxe/tts-server/blob/4903b4a14828549b78676cb9927e0242695d5a06/setup.py#L4-L6
- also needed this to make other impotrs inside styletts work: https://github.com/lxe/tts-server/blob/4903b4a14828549b78676cb9927e0242695d5a06/tts_server/tts.py#L20-L23
I think a lot of this styletts code needs some relative module imports and some other cleanup
from styletts2.
I think I can move this to discussion now, as making a pip package would inevitably ruin the current MIT license status unless we have a good MIT licensed phonemizer alternative.
from styletts2.
Related Issues (20)
- Strange Loss Behavior During Stage Two Training - Not Decreasing after Diff Epoch HOT 2
- Finetune on ljspeech or libritts? HOT 1
- Better LJSpeech or LibriTTS for finetuning a single speaker voice? Or training from scratch with not so much data? HOT 3
- SLM Adversarial Training did not start when finetuning HOT 11
- Second stage training with smaller window size HOT 1
- Possible Bug in Style Diffusion Inference Code
- Issue with impropper pauses and random bursts of noise
- Cannot Convert float NaN to integer HOT 1
- HELP WANTED!!!!!!!!!!! HOT 3
- asr negative loss
- Resuming finetuning uses second to last epoch
- Help Wanted For Stage-1 HOT 2
- Inference with multilingual PL-BERT Model HOT 4
- During training, the graphics memory has been continuously increasing
- May be a bug? input parameters for model.predictor_encoder and model.style_encoder in train_finetune.py
- S_loss = 0 ... why? HOT 2
- Inference Error: context_features exists but no features provided HOT 1
- Speech conditioning like tortoise TTS HOT 1
- FP8 Fine Tuning Crashes HOT 1
- Error Message After Using a fine tuned ASR Model
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 styletts2.