danruta / xva-trainer Goto Github PK
View Code? Open in Web Editor NEWUI app for training TTS/VC machine learning models for xVASynth, with several audio pre-processing tools, and dataset creation/management.
xva-trainer's People
Contributors
Stargazers
Watchers
Forkers
bunglepaws yuripourre-forks diagnostikon pendrokar grumpyben hololeo sariohara smallbutfine cybersys colorfingers saradark iamleon121 swordlegend randomais jak12-3xva-trainer's Issues
Training started, no error but not working
stucked there for long time, just nothing happening
Running Whisper from GPU
Hello! Is it possible to run Whisper from GPU? When transcribing the audios, I see that it uses my CPU and takes forever. I haven't seen the option to switch Whisper from CPU to GPU. I have a RTX 3060 Ti with CUDA installed. Thank you.
"Only latest" number input value is lost after restart
Just a minor thing, but the input becomes empty after restarting the app.
Allow manually saving checkpoints
Given that it can take quite some time to train 2500 steps, it would be convenient to create manual checkpoints so training can resume from that.
Steam release 1.2.0 seems to be broken
Multiple issues. Checking data files through Steam didn't show any error. Cleaning up the dataset didn't help.
- I've got this stacktrace after starting a new training from scratch:
Traceback (most recent call last):
File "server.py", line 227, in handleTrainingLoop
File "python\xvapitch\xva_train.py", line 137, in handleTrainer
File "python\xvapitch\xva_train.py", line 554, in start
File "python\xvapitch\xva_train.py", line 601, in iteration
File "python\xvapitch\xva_train.py", line 377, in init
File "python\xvapitch\xva_train.py", line 1206, in setup_dataloaders
File "C:\Program Files (x86)\Steam\steamapps\common\xVATrainer\.\resources\app\python\xvapitch\util.py", line 410, in get_language_weighted_sampler
return WeightedRandomSampler(dataset_samples_weight, len(dataset_samples_weight))
File "torch\utils\data\sampler.py", line 186, in __init__
raise ValueError("num_samples should be a positive integer "
ValueError: num_samples should be a positive integer value, but got num_samples=0
The line numbers there don't match up with xva_train.py, changes to that file to debug this are completely ignored, whereas changes to e.g. dataset.py are working fine. Throwing an exception in read_datasets shows that at least one point it's returning the correct dataset.
- The UI is still broken when adding new trainings, it seems the list of trainings must be cleared in order to be able to add a new training.
Speaker diarization in 1.2.0+ does not work
UI error message:
ERROR:Traceback (most recent call last):
File "server.py", line 200, in websocket_handler
File "python\make_srt\model.py", line 91, in make_srt
KeyError: 'diarization'
server.log of version 1.2.0
Traceback (most recent call last):
File "python\models_manager.py", line 37, in init_model
File "python\speaker_diarization\model.py", line 26, in __init__
File "python\speaker_diarization\model.py", line 129, in load_model
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pyannote\audio\features\__init__.py", line 33, in <module>
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pyannote\audio\features\base.py", line 38, in <module>
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pyannote\database\__init__.py", line 37, in <module>
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pyannote\database\database.py", line 31, in <module>
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pyannote\database\util.py", line 32, in <module>
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pandas\__init__.py", line 22, in <module>
from pandas.compat import (
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pandas\compat\__init__.py", line 15, in <module>
from pandas.compat.numpy import (
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pandas\compat\numpy\__init__.py", line 7, in <module>
from pandas.util.version import Version
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pandas\util\__init__.py", line 1, in <module>
from pandas.util._decorators import ( # noqa
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pandas\util\_decorators.py", line 14, in <module>
from pandas._libs.properties import cache_readonly # noqa
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pandas\_libs\__init__.py", line 13, in <module>
from pandas._libs.interval import Interval
File "pandas\_libs\interval.pyx", line 1, in init pandas._libs.interval
File "pandas\_libs\hashtable.pyx", line 1, in init pandas._libs.hashtable
File "pandas\_libs\missing.pyx", line 1, in init pandas._libs.missing
File "PyInstaller\loader\pyimod03_importers.py", line 495, in exec_module
File "pandas\_libs\tslibs\__init__.py", line 31, in <module>
from pandas._libs.tslibs.conversion import (
File "pandas\_libs\tslibs\conversion.pyx", line 1, in init pandas._libs.tslibs.conversion
ModuleNotFoundError: No module named 'pandas._libs.tslibs.base'
server.log of version 1.2.1
Traceback (most recent call last):
File "python\models_manager.py", line 37, in init_model
File "python\speaker_diarization\model.py", line 26, in __init__
File "python\speaker_diarization\model.py", line 129, in load_model
ImportError: cannot import name 'Pretrained' from 'pyannote.audio.features' (C:\Program Files (x86)\Steam\steamapps\common\xVATrainer\resources\app\cpython_gpu\pyannote\audio\features\__init__.pyc)
Improve training quality / synthesis
Hi, I see that the PRIORS datasets are synthetic. I plan to replace them with more natural sounding datasets (either synthetic and/or human). This will help for a better and more natural pronunciation and intonation in voice synthesis?
I also plan to make an improvement on Arpabet, since it has a problem with the double R ("RR"), in Spanish, and does not read accents.
Is it possible to improve the dictionary?
I have a mod I made some time ago for Tacotron for the Spanish language, but I don't know if it can be implemented here. I leave the link to the files below. Thanks!
https://drive.google.com/file/d/19AGqgfWiMc8MYHuH_705phCbm8-GGIDa/view?usp=drive_link
Error While Training
Settings:
Output:
18:41:18 | New Session
18:41:18 | No graphs.json file found. Starting anew.
18:41:18 | Dataset: C:/Program Files (x86)/Steam/steamapps/common/xVATrainer/resources/app/datasets//rdfvd_paimon
18:41:18 | Language: English
18:41:18 | Checkpoint: ./resources/app/python/xvapitch/pretrained_models/xVAPitch_5820651.pt
18:41:18 | CUDA device IDs: 0
18:41:18 | FP16: Disabled
18:41:18 | Batch size: 6 (Base: 6, GPUs mult: 1) | GAM: 67 -> (402) | Target: 400
18:41:18 | Outputting model backups every 3 checkpoints
18:41:19 | Loading model and optimizer state from ./resources/app/python/xvapitch/pretrained_models/xVAPitch_5820651.pt
18:41:20 | New voice
18:41:20 | Workers: 3
18:41:38 | Fine-tune dataset files: 7
18:45:00 | Priors datasets files: 179007 | Number of datasets: 28
Error:
Traceback (most recent call last):
File "server.py", line 227, in handleTrainingLoop
File "python\xvapitch\xva_train.py", line 137, in handleTrainer
File "python\xvapitch\xva_train.py", line 557, in start
File "python\xvapitch\xva_train.py", line 604, in iteration
File "python\xvapitch\xva_train.py", line 391, in init
File "C:\Program Files (x86)\Steam\steamapps\common\xVATrainer\.\resources\app\python\xvapitch\get_dataset_emb.py", line 18, in get_emb
kmeans = KMeans(n_clusters=n_clusters, random_state=0).fit(embs)
File "sklearn\cluster\_kmeans.py", line 1376, in fit
self._check_params(X)
File "sklearn\cluster\_kmeans.py", line 1307, in _check_params
super()._check_params(X)
File "sklearn\cluster\_kmeans.py", line 828, in _check_params
raise ValueError(
ValueError: n_samples=7 should be >= n_clusters=10.
Instructions for running from source
Title. I'm pretty sure this is an electron app but I have no idea which of these files to do anything with.
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.