Home
Artists
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register
Partychan SimpleX Chat ThePornDude
Home Artists Posts Import Register
Join the new SimpleX Chat Group!

1-Click INSTALL Coqui Text-To-Speech For Webui (Patreon)

Published:
2023-12-02 18:15:57
Imported:
2023-12
Tags:

Downloads

Content

Hey everyone! I've created a 1-click auto installer (or 2 clicks technically because of the sequence of actions needed) for the Coqui Text-To-Speech Extension for the Oobabooga Text-Generation-Webui. An INCREDIBLE text-to-speech tool that allows you to COPY ANY VOICES WITH JUST 6-10 SECONDS OF AUDIO!
It supports 16 different languages (English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt), Polish (pl), Turkish (tr), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (ko) ) that you can run on you computer inside the Oobabooga Text-Generation-Webui.

And these file automates the entire install process!

Here's how it works:

1. Download the zip archive, unzip it, then select the 4 .bat files inside, drag and drop them inside the Text-Generation-Webui folder, then run the first file called "1_INSTALL-REQ.bat" which will automatically install the requirements needed for the extension to work. Once it asks you to press any key, it will automatically launch the webui.
2. Go to the session tab inside the webui, check the coqui_tts checkbox and click on the "Apply flags/extensions and restart" button to restart the webui. It will then ask you to accept the terms of service, just type "y" and press enter which will then download the tts model.
3. Once the model is downloaded, launch the second file called "2_UPDATE-TTS.bat" which will update the tts and solve the automatic re-download of the model each time you relaunch the webui, once it asks you to press any key, it will automatically download the 2.0.2 version model and automatically replace the bad models located in the appdata folder.
4. Launch the webui and activate the extension again
5. ???
6. Profit 😎


And 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...huh... fun *wink*😉 *wink* 😉!

Files

Comments

Anonymous

new wheel issue

Anonymous

NotImplementedError: Cannot copy out of meta tensor; no data! when loading models using TheBloke_mistral-ft-optimized-1218-AWQ my gpu RTX3050M 4GB

Aitrepreneur
>>125121479

your GPU might not have enough vram to run that model, you can try this one: TheBloke/Mistral-Pygmalion-7B-GPTQ:gptq-4bit-32g-actorder_True just copy and paste that line in the model download field, and then select the exllama loader once the model is downloaded but 4gb of vram is really not a lot for running local llms

Anonymous

Hopefully they can get Coqui working with SillyTavern

Elijah Matthew Moses

Not sure what this means but when I go to launch coqui_tts after using the one click installer from the patreon page, it gives me this error: LLVM ERROR: Symbol not found: __svml_cosf8_ha Please, how does one fix this? Windows 10 Pro Processor Intel(R) Core(TM) i9-9900K CPU @ 3.60GHz 3.60 GHz Nvidia GeForce RTX 3090 Installed RAM 128 GB

Anonymous

Please a colab version for the poor souls who don't have a good PC. 🫶🏾

Anonymous

I can't install this for shit locally, I am absolutely pissed TFO lol... Anyone live in Los Angeles that could help? Not a fucking wierdo, just asking for help don't get it twisted!

Bradford Klipan

Hey Everyone. First of all, I wanted to give a big Thank You to AItrepreneur. I have seen there are a lot of videos on youTube that talk about doing AI in the cloud, but I wanted to do AI on my home computer, and for that, AItrepreneur is the best channel I have seen! Unfortunately, I was unable to get Oobabooga to work with my GPU on my desktop, but I was able to get it working on my laptop with my CPU. I was also able to get Coqui running on my laptop also with CPU, but I had to go into a certain file and change Device: "cuda" to "cpu". I didn't know if doing that would work, as I was just guessing as to what to do. But it did work! I have a lot of catching up to do with all of the different AI programs, as I am a bit of a latecomer it seems.

Aitrepreneur
>>127382037

Happy to see that it worked at least, it's true that you often need a powerful GPU for these ai tools but at least you can run that on your CPU as well so that's also pretty cool :)

Anonymous

i have this problem: ERROR: Could not open requirements file: [Errno 2] No such file or directory: 'extensions\\coqui_tts\\requirements.txt'

gillian

Any ideas?

gillian

I clean installed your one click ooba from here and used your 4 file (2 click) for coqui tts but when i apply flags/extensions and restart I did not get the accept terms of service prompt and coqui wouldn't load. I did the 2Update and still coqui appears in the session but will not load. What am I doing wrong?

Aitrepreneur
>>127786855

If you have issues I actually recommend installing Sillytavern instead, not only you get the same tts but you also get the great UI and everything in between, just use the 1 click installer for that

Anonymous

After setting all for the local uncensored model via oobabooga, and clicking on "1_INSTALL-REQ.bat", it installed everything but i got this error in the cmd (windows 10): LLVM ERROR: Symbol not found: __svml_cosf8_ha python 3.9 After that I can't enter the web GUI: http://127.0.0.1:7860/ ERR_CONNECTION_REFUSED My oobabooga worked until I downloaded official one click script and this happened... please help

Aitrepreneur
>>129585613

try download this file: https://we.tl/t-eJN4nn3nn1 and place it in the system32 folder C:\Windows\System32

Anonymous

Please update the scripts since the windows_update.bat is somehow installing pandas 2.2 : "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. tts 0.22.0 requires pandas<2.0,>=1.4, but you have pandas 2.2.0 which is incompatible." and then when i run 2_UPDATE-TTS.bat, it says: " Installing collected packages: pandas Attempting uninstall: pandas Found existing installation: pandas 2.2.0 Uninstalling pandas-2.2.0: Successfully uninstalled pandas-2.2.0 Successfully installed pandas-1.5.3" but then the script is downloading a 50+mb file every time. My guess is that some of the scripts are having different pandas version.

Aitrepreneur
>>129615921

I don't personally have this error, also the issue is from the coqui github repository not from the installer

Virtamouse

I sent you a DM. Is there a way to use this for longer format Speech Synthesis? I want to be able to use a voice I cloned and save what I type out. Longer format, not chatting with a bot?

Anonymous
>>130030688

I have the same questions. Id like to save the longer format for making youtube videos with soley voice AI. Is that possible with this?

Akshay

Can you provide a collab notebook for this?

Relven

Silero TTS cache not found at C:\Users\MPG/.cache\torch\hub. Attempting to download... Using cache found in C:\Users\MPG/.cache\torch\hub\snakers4_silero-models_master 00:58:16-731395 ERROR Failed to load the extension "silero_tts". Traceback (most recent call last): File "C:\Users\MPG\Tavern\text-generation-webui\modules\extensions.py", line 46, in load_extensions extension.setup() File "C:\Users\MPG\Tavern\text-generation-webui\extensions\silero_tts\script.py", line 148, in setup model = load_model() ^^^^^^^^^^^^ File "C:\Users\MPG\Tavern\text-generation-webui\extensions\silero_tts\script.py", line 61, in load_model model, example_text = torch.hub.load(repo_or_dir='snakers4/silero-models', model='silero_tts', language=languages[params['language']]["lang_id"], speaker=params['model_id']) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\MPG\Tavern\text-generation-webui\installer_files\env\Lib\site-packages\torch\hub.py", line 566, in load model = _load_local(repo_or_dir, model, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\MPG\Tavern\text-generation-webui\installer_files\env\Lib\site-packages\torch\hub.py", line 595, in _load_local model = entry(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\MPG/.cache\torch\hub\snakers4_silero-models_master\src\silero\silero.py", line 51, in silero_tts from omegaconf import OmegaConf ModuleNotFoundError: No module named 'omegaconf' Running on local URL: http://127.0.0.1:7860 ___________________________________ So it's working but don't run silero_tts. And I have no extension 11labs

Aitrepreneur
>>133640443

this error means that you have tried to activate the silero extension in the session tab, disable it. 11labs was removed from the text gen webui, for this you need to use sillytavern

gillian

whisper error when i try to record reply? I get this on updating : ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. tts 0.21.3 requires pandas<2.0,>=1.4, but you have pandas 2.2.1 which is incompatible. If this is the cause how do I resolve

Brett Anderson

can you help with this issue

Brett Anderson

Install deepspeed for windows for python 3.10.x and CUDA 11.8 Traceback (most recent call last): File "D:\ultimate tts installer\xtts-webui\scripts\modeldownloader.py", line 4, in import requests ModuleNotFoundError: No module named 'requests' Install complete. Press any key to continue . . .

Aitrepreneur
>>139222328

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