Home Artists Posts Import Register

Downloads

Content

Hey everyone! I've created a 1-click installer for the 3 TTS WEBUI (Xtts webui, Xtts finetune webui and Xtts RVC UI). These open-source tools will allow you to make the best Ai text-to-speech voices on your local computer with 3 different methods and 3 Webui! So that no matter who you are and what your goals are, you get the best quality possible! Bye-bye elevenlabs!

Watch the video about The ULTIMATE LOCAL TTS: https://youtu.be/ds5LLIt5OLM

The installer of course automates the entire install process for the 3 WEBUI!

Here's how it works:

1. Download the FFMPEG-INSTALL AS ADMIN.bat and RUN THIS AS ADMINISTRATOR (right click---> run as admin) this will download FFMPEG and add it to path, no need to use this if you already have ffmpeg installed and added to path of course.

2. Download the installer (ULTIMATE-TTS_AUTO_INSTALLER.bat)

2. Create a new folder on your computer and place the installer inside

3. Launch the installer

4. Select which webui you want to install (type 4 if you want to install them all)

5. After each single install, close the current install window so that the next one can start (press n if it asks you if you want to terminate the batch job) until all webui are installed

6.????

7. Profit  😎


As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some fun😉!

Files

Comments

Tohnbon

Collecting gradio==4.13.0 (from -r .\requirements.txt (line 1)) Downloading gradio-4.13.0-py3-none-any.whl.metadata (15 kB) ERROR: Could not find a version that satisfies the requirement torch==2.1.1 (from versions: 2.2.0, 2.2.1, 2.2.2, 2.3.0) ERROR: No matching distribution found for torch==2.1.1 Looking in indexes: https://download.pytorch.org/whl/cu118 ERROR: Could not find a version that satisfies the requirement torch==2.1.1+cu118 (from versions: 2.2.0+cu118, 2.2.1+cu118, 2.2.2+cu118, 2.3.0+cu118) ERROR: No matching distribution found for torch==2.1.1+cu118 Install deepspeed for windows for python 3.10.x and CUDA 11.8 Traceback (most recent call last): File "C:\Users\Owner\Desktop\TTS\xtts-webui\scripts\modeldownloader.py", line 4, in import requests ModuleNotFoundError: No module named 'requests' Install complete. Press any key to continue . . . What do I do?

Aitrepreneur

open a command prompt window and type: python -m pip install --upgrade pip Then 1) Open System Properties: Right-click on the Start button and select System. Click on Advanced system settings on the left side. In the System Properties window, click on the Environment Variables button near the bottom. Add New System Variable: In the Environment Variables window, under the "System variables" section, click on New. For the Variable name, enter PYTHONUTF8. For the Variable value, enter 1. Click OK to close the dialog box and exit. 2) Open Control Panel and go to Clock and Region. Click on Region. In the Region window, go to the Administrative tab. Click on the Change system locale button. Ensure that the checkbox for Beta: Use Unicode UTF-8 for worldwide language support is checked. Click OK and then Restart the computer. You might also have a bad initial python install, you need to uninstall your current python installation and reinstall it correctly. Go to the add and remove programs, search for python and uninstall both the current python version and the python install program. Once this is done, go here and download this installer: https://www.python.org/ftp/python/3.10.6/python-3.10.6-amd64.exe Run it and check the “Add python 3.10 to Path” checkbox and continue with the installation. You can check that the right python version is installed by opening a new command prompt window and typing: python --version and it should give you the 3.10.6 version Then just relaunch the 1-click installer in a new folder and try again.

evil chucky69

re: xtts-finetune-webui while trying to create a dataset from a wav file i keep getting this error= File "C:\AI ULTIMATE TTS x 4\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 767, in encode return self.model.encode(features, to_cpu=to_cpu) RuntimeError: Library cublas64_12.dll is not found or cannot be loaded "AI ULTIMATE TTS x 4" being the folder where the 3 programs were installed to/from. according to my checks i have python 3.10.6 version installed (tho during install of all 3 programs, it says there is an update! (v3.10.6 available!) any suggestions for a cure are welcome!

Little_me

not sure how to solve this. Trying to execute start_xtts_webui.bat file and I get this... help? :( Traceback (most recent call last): File "C:\Users\me\Documents\Aitrepreneur Installers\xtts-webui\app.py", line 1, in from scripts.modeldownloader import install_deepspeed_based_on_python_version File "C:\Users\me\Documents\Aitrepreneur Installers\xtts-webui\scripts\modeldownloader.py", line 4, in import requests ModuleNotFoundError: No module named 'requests'

Aitrepreneur

open a command prompt window and type: python -m pip install --upgrade pip Then 1) Open System Properties: Right-click on the Start button and select System. Click on Advanced system settings on the left side. In the System Properties window, click on the Environment Variables button near the bottom. Add New System Variable: In the Environment Variables window, under the "System variables" section, click on New. For the Variable name, enter PYTHONUTF8. For the Variable value, enter 1. Click OK to close the dialog box and exit. 2) Open Control Panel and go to Clock and Region. Click on Region. In the Region window, go to the Administrative tab. Click on the Change system locale button. Ensure that the checkbox for Beta: Use Unicode UTF-8 for worldwide language support is checked. Click OK and then Restart the computer. then redo the installation IF you still get the error, you can try this after doing the install: Go inside the main folder, click on the folder path, type “cmd” press enter, this will bring the command prompt window and inside you’re gonna type: venv\Scripts\activate press enter pip install requests press enter then relaunch the webui

ZY Swanson

I may be an idiot, but after I've downloaded everything and done the setup installation for the steps said for the AI, what do I do actually to start using the AI?

HunterSHC

Hey is there a way to connect the XTTS-RVC-UI to SillyTavern? If yes could you please tell me how to do so

Monsieur Pimpant

hello, i've run into some problems, first the installation happened to be in system32, i had to move the folders into the desired one, then i'm having this error with xtts finetune; The data processing was interrupted due an error !! Please check the console to verify the full error message! Error summary: Traceback (most recent call last): File "F:\09_IA\03_XTTS\xtts-finetune-webui\xtts_demo.py", line 246, in preprocess_dataset train_meta, eval_meta, audio_total_size = format_audio_list(audio_path, whisper_model = whisper_model, target_language=language, out_path=out_path, gradio_progress=progress) File "F:\09_IA\03_XTTS\xtts-finetune-webui\utils\formatter.py", line 131, in format_audio_list segments = list(segments) File "C:\Users\monsi\AppData\Local\Programs\Python\Python310\lib\site-packages\faster_whisper\transcribe.py", line 1106, in restore_speech_timestamps for segment in segments: File "C:\Users\monsi\AppData\Local\Programs\Python\Python310\lib\site-packages\faster_whisper\transcribe.py", line 511, in generate_segments encoder_output = self.encode(segment) File "C:\Users\monsi\AppData\Local\Programs\Python\Python310\lib\site-packages\faster_whisper\transcribe.py", line 762, in encode return self.model.encode(features, to_cpu=to_cpu) RuntimeError: Library cublas64_12.dll is not found or cannot be loaded

Aitrepreneur

It's because you ran the installer as admin, don't do that, run it normally. For the error, you need to install cuda 12 from the nvidia website

Robert Hulsteijn

To create a public link, set `share=True` in `launch()`. IMPORTANT: You are using gradio version 4.9.1, however version 4.29.0 is available, please upgrade. -------- Existing language matches target language Loading Whisper Model! Existing training metadata found and loaded. Existing evaluation metadata found and loaded. Segments from Katja have been previously processed; skipping... Dataset Processed! Traceback (most recent call last): File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\queueing.py", line 459, in call_prediction output = await route_utils.call_process_api( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api output = await app.get_blocks().process_api( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\blocks.py", line 1533, in process_api result = await self.call_function( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\blocks.py", line 1151, in call_function prediction = await anyio.to_thread.run_sync( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 2177, in run_sync_in_worker_thread return await future File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 859, in run result = context.run(func, *args) File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\utils.py", line 678, in wrapper response = f(*args, **kwargs) File "C:\AI\xtts-finetune-webui\xtts_demo.py", line 339, in train_model os.remove(run_dir) PermissionError: [WinError 5] Toegang geweigerd: 'C:\\AI\\xtts-finetune-webui\\finetune_models\\run' Traceback (most recent call last): File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\queueing.py", line 459, in call_prediction output = await route_utils.call_process_api( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api output = await app.get_blocks().process_api( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\blocks.py", line 1533, in process_api result = await self.call_function( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\blocks.py", line 1151, in call_function prediction = await anyio.to_thread.run_sync( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 2177, in run_sync_in_worker_thread return await future File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 859, in run result = context.run(func, *args) File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\utils.py", line 678, in wrapper response = f(*args, **kwargs) File "C:\AI\xtts-finetune-webui\xtts_demo.py", line 339, in train_model os.remove(run_dir) PermissionError: [WinError 5] Toegang geweigerd: 'C:\\AI\\xtts-finetune-webui\\finetune_models\\run' The above exception was the direct cause of the following exception: Traceback (most recent call last): File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\queueing.py", line 497, in process_events response = await self.call_prediction(awake_events, batch) File "C:\AI\xtts-finetune-webui\venv\lib\site-packages\gradio\queueing.py", line 468, in call_prediction raise Exception(str(error) if show_error else None) from error Exception: None

Solitary Robot

does anyone get the deepspeed error? no module named?

Peter

Hi, When I open start_xtts_webui.bat I get following error: File "c:\Users\Peter\AppData\Local\Programs\Python\Python310\xtts-webui\app.py", line 1, in from scripts.modeldownloader import install_deepspeed_based_on_python_version File "c:\Users\Peter\AppData\Local\Programs\Python\Python310\xtts-webui\scripts\modeldownloader.py", line 4, in import requests ModuleNotFoundError: No module named 'requests' Press any key to continue . . .

Aitrepreneur

open a command prompt window and type: python -m pip install --upgrade pip Then 1) Open System Properties: Right-click on the Start button and select System. Click on Advanced system settings on the left side. In the System Properties window, click on the Environment Variables button near the bottom. Add New System Variable: In the Environment Variables window, under the "System variables" section, click on New. For the Variable name, enter PYTHONUTF8. For the Variable value, enter 1. Click OK to close the dialog box and exit. 2) Open Control Panel and go to Clock and Region. Click on Region. In the Region window, go to the Administrative tab. Click on the Change system locale button. Ensure that the checkbox for Beta: Use Unicode UTF-8 for worldwide language support is checked. Click OK and then Restart the computer. then redo the installation

John Greggs

Hi, I have been trying to run this install, but I keep getting an error saying that python can't build wheels for TTS. "note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for tts Failed to build tts ERROR: Could not build wheels for tts, which is required to install pyproject.toml-based projects". I get this error when I try to launch the UI after the install: ModuleNotFoundError: No module named 'requests' I have an RTX 3060 12gb and I have python 3.10.6 installed on my computer.

Aitrepreneur

open a command prompt window and type: python -m pip install --upgrade pip Then 1) Open System Properties: Right-click on the Start button and select System. Click on Advanced system settings on the left side. In the System Properties window, click on the Environment Variables button near the bottom. Add New System Variable: In the Environment Variables window, under the "System variables" section, click on New. For the Variable name, enter PYTHONUTF8. For the Variable value, enter 1. Click OK to close the dialog box and exit. 2) Open Control Panel and go to Clock and Region. Click on Region. In the Region window, go to the Administrative tab. Click on the Change system locale button. Ensure that the checkbox for Beta: Use Unicode UTF-8 for worldwide language support is checked. Click OK and then Restart the computer. then redo the installation

Kevin Weiß

Hello, when I start the finetune webui i get this Error: ERROR: Exception in ASGI application Traceback (most recent call last): File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 265, in __call__ await wrap(partial(self.listen_for_disconnect, receive)) File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 261, in wrap await func() File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 238, in listen_for_disconnect message = await receive() File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 553, in receive await self.message_event.wait() File "C:\Users\kevin\AppData\Local\Programs\Python\Python310\lib\asyncio\locks.py", line 214, in wait await fut asyncio.exceptions.CancelledError: Cancelled by cancel scope 1cc30bccd30 During handling of the above exception, another exception occurred: + Exception Group Traceback (most recent call last): | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 399, in run_asgi | result = await app( # type: ignore[func-returns-value] | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 70, in __call__ | return await self.app(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\fastapi\applications.py", line 1054, in __call__ | await super().__call__(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\applications.py", line 123, in __call__ | await self.middleware_stack(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\middleware\errors.py", line 186, in __call__ | raise exc | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\middleware\errors.py", line 164, in __call__ | await self.app(scope, receive, _send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\middleware\cors.py", line 85, in __call__ | await self.app(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\middleware\exceptions.py", line 65, in __call__ | await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\_exception_handler.py", line 64, in wrapped_app | raise exc | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\_exception_handler.py", line 53, in wrapped_app | await app(scope, receive, sender) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 756, in __call__ | await self.middleware_stack(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 776, in app | await route.handle(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 297, in handle | await self.app(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 77, in app | await wrap_app_handling_exceptions(app, request)(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\_exception_handler.py", line 64, in wrapped_app | raise exc | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\_exception_handler.py", line 53, in wrapped_app | await app(scope, receive, sender) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 75, in app | await response(scope, receive, send) | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 258, in __call__ | async with anyio.create_task_group() as task_group: | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 680, in __aexit__ | raise BaseExceptionGroup( | exceptiongroup.ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception) +-+---------------- 1 ---------------- | Traceback (most recent call last): | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 261, in wrap | await func() | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 250, in stream_response | async for chunk in self.body_iterator: | File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\gradio\routes.py", line 602, in sse_stream | raise HTTPException( | fastapi.exceptions.HTTPException: 404: Session not found. +------------------------------------ I tried to reinstall but it keept comming back

Aitrepreneur

First what is your python version? Secondly, NEVER install in a OneDrive subfolder, it can cause issues during install

Professor Chris G

Before you get upset with me I redid everything, installed an NVIDIA Geforce GPU and everything seems to have installed correctly :) but on the finetune app I keep getting an error message when I upload my audio: The data processing was interrupted due an error !! Please check the console to verify the full error message! Error summary: Traceback (most recent call last): File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\xtts_demo.py", line 246, in preprocess_dataset train_meta, eval_meta, audio_total_size = format_audio_list(audio_path, whisper_model = whisper_model, target_language=language, out_path=out_path, gradio_progress=progress) File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\utils\formatter.py", line 131, in format_audio_list segments = list(segments) File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 1111, in restore_speech_timestamps for segment in segments: File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 508, in generate_segments encoder_output = self.encode(segment) File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 767, in encode return self.model.encode(features, to_cpu=to_cpu) RuntimeError: Library cublas64_12.dll is not found or cannot be loaded

Aitrepreneur

😱😱 YES! I AM EXTREMELY UPSET! Jk 😄 To solve this error you just need to dl and install cuda 12 from the nvidia website :) https://developer.nvidia.com/cuda-downloads

Professor Chris G

Now for some reason I'm getting this error message: ERROR: Exception in ASGI application Traceback (most recent call last): File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 265, in __call__ await wrap(partial(self.listen_for_disconnect, receive)) File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 261, in wrap await func() File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 238, in listen_for_disconnect message = await receive() File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 553, in receive await self.message_event.wait() File "C:\Users\chris\AppData\Local\Programs\Python\Python310\lib\asyncio\locks.py", line 214, in wait await fut asyncio.exceptions.CancelledError: Cancelled by cancel scope 22ffe4069e0 During handling of the above exception, another exception occurred: + Exception Group Traceback (most recent call last): | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 399, in run_asgi | result = await app( # type: ignore[func-returns-value] | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 70, in __call__ | return await self.app(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\fastapi\applications.py", line 1054, in __call__ | await super().__call__(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\applications.py", line 123, in __call__ | await self.middleware_stack(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\middleware\errors.py", line 186, in __call__ | raise exc | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\middleware\errors.py", line 164, in __call__ | await self.app(scope, receive, _send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\middleware\cors.py", line 85, in __call__ | await self.app(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\middleware\exceptions.py", line 65, in __call__ | await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\_exception_handler.py", line 64, in wrapped_app | raise exc | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\_exception_handler.py", line 53, in wrapped_app | await app(scope, receive, sender) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 756, in __call__ | await self.middleware_stack(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 776, in app | await route.handle(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 297, in handle | await self.app(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 77, in app | await wrap_app_handling_exceptions(app, request)(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\_exception_handler.py", line 64, in wrapped_app | raise exc | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\_exception_handler.py", line 53, in wrapped_app | await app(scope, receive, sender) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\routing.py", line 75, in app | await response(scope, receive, send) | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 258, in __call__ | async with anyio.create_task_group() as task_group: | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 680, in __aexit__ | raise BaseExceptionGroup( | exceptiongroup.ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception) +-+---------------- 1 ---------------- | Traceback (most recent call last): | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 261, in wrap | await func() | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 250, in stream_response | async for chunk in self.body_iterator: | File "C:\Users\chris\Documents\VoiceClone\xtts-finetune-webui\venv\lib\site-packages\gradio\routes.py", line 602, in sse_stream | raise HTTPException( | fastapi.exceptions.HTTPException: 404: Session not found.

Kevin Weiß

when training a xxts-finetune model i get this message: "[!] Warning: The text length exceeds the character limit of 253 for language 'de', this might cause truncated audio." Can I fix that or does that not matter?

Mr Hussain

I have everything working i just need help with the xtts finetune ui - the problem is when i try to launch this it says ' cannot find empty port in range 5003-5003. You can specify a different port by setting the GRADIO_SERVER_PORT environment variable or passing the 'server_port' parameter to 'launch()'

Aitrepreneur

if you edit the start.bat file on line 5 you can add the --port argument followed by the port number you want to use so in the end you get something like python xtts_demo.py --port 420

Kevin Weiß

Sorry to bother you again, but I'm having trouble with the XTTS fine-tune UI, and it's giving me headaches. I managed to resolve the issue where I encountered an error message like this: ERROR: Exception in ASGI application Traceback (most recent call last): File "C:\Users\kevin\OneDrive\Desktop\XTTS\xtts-finetune-webui\venv\lib\site-packages\starlette\responses.py", line 265, in __call__ await wrap(partial(self.listen_for_disconnect, receive)) ... I fixed it simply by reopening the XTTS fine-tune UI and retrying the process. The problem I'm facing now is related to the XTTS fine-tune UI incorrectly detecting the language, which causes the model to switch languages unexpectedly. When I review the final result of the fine-tuned model, the original German language doesn't perform well. However, the English results seem to be working perfectly. Is there a way of locking the model to a specific language other than the options when u start the XXTS finetune ui?

Aitrepreneur

You can change the language when uploading the audio file in the first step, try also the 03 model if you plan on training german, it apparently work better with it

Atticus Xey

I assume that I installed, but when I try running, this is what I get. Traceback (most recent call last): File "D:\Audio_1\xtts-webui\app.py", line 1, in from scripts.modeldownloader import install_deepspeed_based_on_python_version File "D:\Audio_1\xtts-webui\scripts\modeldownloader.py", line 4, in import requests ModuleNotFoundError: No module named 'requests' Press any key to continue . . .

Aitrepreneur

open a command prompt window and type: python -m pip install --upgrade pip Then 1) Open System Properties: Right-click on the Start button and select System. Click on Advanced system settings on the left side. In the System Properties window, click on the Environment Variables button near the bottom. Add New System Variable: In the Environment Variables window, under the "System variables" section, click on New. For the Variable name, enter PYTHONUTF8. For the Variable value, enter 1. Click OK to close the dialog box and exit. 2) Open Control Panel and go to Clock and Region. Click on Region. In the Region window, go to the Administrative tab. Click on the Change system locale button. Ensure that the checkbox for Beta: Use Unicode UTF-8 for worldwide language support is checked. Click OK and then Restart the computer. then redo the installation

Atticus Xey

I went through a number of steps, uninstalling Python, then reinstalling from the website, then I tried to reinstall, and it goes back to the this: Collecting gradio==4.13.0 (from -r .\requirements.txt (line 1)) Using cached gradio-4.13.0-py3-none-any.whl.metadata (15 kB) ERROR: Could not find a version that satisfies the requirement torch==2.1.1 (from versions: 2.2.0, 2.2.1, 2.2.2, 2.3.0, 2.3.1) ERROR: No matching distribution found for torch==2.1.1 Looking in indexes: https://download.pytorch.org/whl/cu118 ERROR: Could not find a version that satisfies the requirement torch==2.1.1+cu118 (from versions: 2.2.0+cu118, 2.2.1+cu118, 2.2.2+cu118, 2.3.0+cu118, 2.3.1+cu118) ERROR: No matching distribution found for torch==2.1.1+cu118 Install deepspeed for windows for python 3.10.x and CUDA 11.8 Traceback (most recent call last): File "D:\Audio_1\xtts-webui\scripts\modeldownloader.py", line 4, in import requests ModuleNotFoundError: No module named 'requests' Install complete. Press any key to continue . . .

Aitrepreneur

1) What is your python version? You need the python 3.10.11. First, you need to uninstall your current python installation and reinstall it correctly. Go to the add and remove programs, search for python and uninstall both the current python version and the python install program. Once this is done, go here and download this installer: https://www.python.org/ftp/python/3.10.11/python-3.10.11-amd64.exe Run it and check the “Add python 3.10 to Path” checkbox and continue with the installation. You can check that the right python version is installed by opening a new command prompt window and typing: python --version and it should give you the 3.10.11 version 2) Have you followed the instruction I gave in the other comment? "open a command prompt window and type: python -m pip install --upgrade pip Then 1) Open System Properties: Right-click on the Start button and select System. Click on Advanced system settings on the left side. In the System Properties window, click on the Environment Variables button near the bottom. Add New System Variable: In the Environment Variables window, under the "System variables" section, click on New. For the Variable name, enter PYTHONUTF8. For the Variable value, enter 1. Click OK to close the dialog box and exit. 2) Open Control Panel and go to Clock and Region. Click on Region. In the Region window, go to the Administrative tab. Click on the Change system locale button. Ensure that the checkbox for Beta: Use Unicode UTF-8 for worldwide language support is checked. Click OK and then Restart the computer. then redo the installation"

Max Ruh

Unfortunately, no 'start.bat' is wirking / starting. They close immediately. And the 'start_xtts_webui.bat' is givin me this error: "Traceback (most recent call last): File "C:\TTS WEBUI\xtts-webui\app.py", line 1, in from scripts.modeldownloader import install_deepspeed_based_on_python_version File "C:\TTS WEBUI\xtts-webui\scripts\modeldownloader.py", line 10, in from packaging import version ModuleNotFoundError: No module named 'packaging'"

Steve Furness

ULTIMATE-TTS_AUTO_INSTALLER simply installs git and then quits no further prompts no nothin

Santedi

I need to dub the audio into XTTS-RVC-UI? It takes a very long time to dub there. And in xtts-webui the voice is not so high quality

Aitrepreneur

could a multitude of reasons, first open a command prompt window and drag and drop the installer file inside the window, then press enter, this should avoid the window from closing and it will at least give us an error code we can use to troubleshoot the error, make also sure that you have disabled any antivirus/firewall from running and blocking the file/connection. This could also be a bad initial python install, you need to uninstall any of your current python installations and reinstall it correctly. Go to the add and remove programs, search for python and uninstall both the current python version and the python install program. Once this is done, go here and download this installer: https://www.python.org/ftp/python/3.10.11/python-3.10.11-amd64.exe Run it and check the “Add python 3.10 to Path” checkbox and continue with the installation. You can check that the right python version is installed by opening a new command prompt window and typing: python --version and it should give you the 3.10.11 version Then just relaunch the 1-click installer in a new folder and try again.

Jean-Marc Meyer

And another after Running Pip Install TTS Traceback (most recent call last): File "C:\Users\JM\Downloads\xtts-webui\app.py", line 67, in from xtts_webui import demo File "C:\Users\JM\Downloads\xtts-webui\xtts_webui.py", line 3, in from scripts.tts_funcs import TTSWrapper File "C:\Users\JM\Downloads\xtts-webui\scripts\tts_funcs.py", line 4, in import torchaudio File "C:\Users\JM\Downloads\xtts-webui\venv\lib\site-packages\torchaudio\__init__.py", line 2, in from . import _extension # noqa # usort: skip File "C:\Users\JM\Downloads\xtts-webui\venv\lib\site-packages\torchaudio\_extension\__init__.py", line 38, in _load_lib("libtorchaudio") File "C:\Users\JM\Downloads\xtts-webui\venv\lib\site-packages\torchaudio\_extension\utils.py", line 60, in _load_lib torch.ops.load_library(path) File "C:\Users\JM\Downloads\xtts-webui\venv\lib\site-packages\torch\_ops.py", line 643, in load_library ctypes.CDLL(path) File "C:\Users\JM\AppData\Local\Programs\Python\Python310\lib\ctypes\__init__.py", line 374, in __init__ self._handle = _dlopen(self._name, mode) OSError: [WinError 127] The specified procedure could not be found Press any key to continue . . .

Mark

What do you think of BigVGAN from Nvidia I asked LLAMA about it according to it does Zero Shot TTS? It’s on Hugging Face Spaces from Nvidia its under the MIT License

Aitrepreneur

ok no, there is no need to manually install anything, this types of error means that there was some issues during install. So delete everything and let's start from scratch. First, check your installed python version. Make sure that you have only the python 3.10.11 installed. If not, you need to uninstall your current python installation and reinstall it correctly. Go to the add and remove programs, search for python and uninstall both the current python version and the python install program. Once this is done, go here and download this installer: https://www.python.org/ftp/python/3.10.11/python-3.10.11-amd64.exe Run it and check the “Add python 3.10 to Path” checkbox and continue with the installation. You can check that the right python version is installed by opening a new command prompt window and typing: python --version and it should give you the 3.10.11 version Then just relaunch the 1-click installer in a new folder and try again. Make sure that you don't have any antiviruses/VPN running before launching the installer. And take any notes of any errors or issues you see during install.

Aitrepreneur

BigVGAN is a vocoder that needs to be implemented into a tts project to have effect, in theory it should make the final tts sound better but I haven't seen many project implement it and the one that did, didn't seem to add any significant improvement to the final audio

Robbie Zek

is it neccisarry to install all 3 for one to work. i'm trying to get finetune working but having issues. also i wanna put it in a conda enviroment when i create that enviroment do i need to install the torchstuff and cuda? if its already in the path. thanks

Aitrepreneur

first of all no, you can install one or all of them, up to you. What is the issue you're having? Also no need to put them in a conda env, it already does that in a python env.

Terry Astrial

also for the finetune model, i'm getting this error when i try to create a dataset: Existing language matches target language Loading Whisper Model! Traceback (most recent call last): File "F:\XTTS\xtts-finetune-webui\xtts_demo.py", line 246, in preprocess_dataset train_meta, eval_meta, audio_total_size = format_audio_list(audio_path, whisper_model = whisper_model, target_language=language, out_path=out_path, gradio_progress=progress) File "F:\XTTS\xtts-finetune-webui\utils\formatter.py", line 131, in format_audio_list segments = list(segments) File "F:\XTTS\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 1111, in restore_speech_timestamps for segment in segments: File "F:\XTTS\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 508, in generate_segments encoder_output = self.encode(segment) File "F:\XTTS\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 767, in encode return self.model.encode(features, to_cpu=to_cpu) RuntimeError: Library cublas64_12.dll is not found or cannot be loaded Oddly, i'm not seeing the same dark theme orange button UI you have in your videos. Mine are all basic white buttons and bad design. lol

Aitrepreneur

For the dark theme, you can just add the following to the url: /?__theme=dark so that it looks like this: http://127.0.0.1:7860/?__theme=dark For the runtime error you need to download and install cuda 12 from the Nvidia website

Pumpalooza

Hello Aitrepeneur! I'm having this error when trying to create dataset in the xtts-finetune-webui model: The data processing was interrupted due an error !! Please check the console to verify the full error message! Error summary: Traceback (most recent call last): File "E:\TTS\xtts-finetune-webui\xtts_demo.py", line 246, in preprocess_dataset train_meta, eval_meta, audio_total_size = format_audio_list(audio_path, whisper_model = whisper_model, target_language=language, out_path=out_path, gradio_progress=progress) File "E:\TTS\xtts-finetune-webui\utils\formatter.py", line 131, in format_audio_list segments = list(segments) File "E:\TTS\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 1111, in restore_speech_timestamps for segment in segments: File "E:\TTS\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 508, in generate_segments encoder_output = self.encode(segment) File "E:\TTS\xtts-finetune-webui\venv\lib\site-packages\faster_whisper\transcribe.py", line 767, in encode return self.model.encode(features, to_cpu=to_cpu) RuntimeError: Library cublas64_12.dll is not found or cannot be loaded I used the automatic installation for everything. I have a 3090. I hope you can help me out! Thanks for you time and patience

Lilo

Why am i getting the error HEUR:Trojan.BAT.Agent.gen from your ULTIMATE-TTS_AUTO_INSTALLER file????!!!

Aitrepreneur

It's a false positive virustotal can't see what's inside a bat file, you can do, if you don't trust it you can just edit the file and look inside to see the code

Lilo

I'm getting the ERROR: Traceback (most recent call last): File "C:\Users\name\Downloads\xtts-webui\app.py", line 1, in from scripts.modeldownloader import install_deepspeed_based_on_python_version File "C:\Users\name\Downloads\xtts-webui\scripts\modeldownloader.py", line 4, in import requests ModuleNotFoundError: No module named 'requests' Do you know why i'm getting this from you file when i hit the "start_xtts_webui" batch file ???

Aitrepreneur

You probably have a bad initial python install, uninstall all previous python install you have and then download and install python 3.10.11 and do not forget to check the add python to path checkbox before the installation Then relaunch the installer in a new folder.

JJVR

I got the install and XTTS to work, but now I'm having issue with FINETUNE not training. When I click on STEP 2 - Run The Training I get this: ACCESS IS DENIED File "J:\TTS\xtts-finetune-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 859, in run result = context.run(func, *args) File "J:\TTS\xtts-finetune-webui\venv\lib\site-packages\gradio\utils.py", line 678, in wrapper response = f(*args, **kwargs) File "C:\xtts-finetune-webui\xtts_demo.py", line 339, in train_model os.remove(run_dir) PermissionError: [WinError 5] Access is denied: 'C:\\xtts-finetune-webui\\finetune_models\\run' The above exception was the direct cause of the following exception: Traceback (most recent call last): File "J:\TTS\xtts-finetune-webui\venv\lib\site-packages\gradio\queueing.py", line 497, in process_events response = await self.call_prediction(awake_events, batch) File "J:\TTS\xtts-finetune-webui\venv\lib\site-packages\gradio\queueing.py", line 468, in call_prediction raise Exception(str(error) if show_error else None) from error Exception: None

JJVR

UPDATE: the issue has returned. I got one decent train, and now it's back to saying access denied? Any ideas? File "J:\TTS\XTTS\xtts-finetune-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 859, in run result = context.run(func, *args) File "J:\TTS\XTTS\xtts-finetune-webui\venv\lib\site-packages\gradio\utils.py", line 678, in wrapper response = f(*args, **kwargs) File "J:\TTS\XTTS\xtts-finetune-webui\xtts_demo.py", line 339, in train_model os.remove(run_dir) PermissionError: [WinError 5] Access is denied: 'J:\\TTS\\XTTS\\xtts-finetune-webui\\finetune_models\\run' The above exception was the direct cause of the following exception: Traceback (most recent call last): File "J:\TTS\XTTS\xtts-finetune-webui\venv\lib\site-packages\gradio\queueing.py", line 497, in process_events response = await self.call_prediction(awake_events, batch) File "J:\TTS\XTTS\xtts-finetune-webui\venv\lib\site-packages\gradio\queueing.py", line 468, in call_prediction raise Exception(str(error) if show_error else None) from error Exception: None

Aitrepreneur

Yes it's normal, you need to delete the finetune folder each time you want to train a new audio model