NokiMo
Aitrepreneur
Aitrepreneur

patreon


1-Click INSTALL Coqui Text-To-Speech For Webui

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* 😉!

1-Click INSTALL Coqui Text-To-Speech For Webui

Comments

Did you ever find a solution for this one? I'm running into the exact same problem.

Andrew Wice

Did you ever find a solution to this? I'm running into the exact same issue.

Andrew Wice

Hi I'm having problems getting the 1_INSTALL-REQ.bat to run. It executes then throws this log: Getting requirements to build wheel ... error error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> [167 lines of output] Error compiling Cython file: ------------------------------------------------------------ ... int length cdef class Vocab: cdef Pool mem cpdef readonly StringStore strings ^ ------------------------------------------------------------ spacy\vocab.pxd:28:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef class Vocab: cdef Pool mem cpdef readonly StringStore strings cpdef public Morphology morphology ^ ------------------------------------------------------------ spacy\vocab.pxd:29:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef class Vocab: cdef Pool mem cpdef readonly StringStore strings cpdef public Morphology morphology cpdef public object vectors ^ ------------------------------------------------------------ spacy\vocab.pxd:30:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef class Vocab: cdef Pool mem cpdef readonly StringStore strings cpdef public Morphology morphology cpdef public object vectors cpdef public object _lookups ^ ------------------------------------------------------------ spacy\vocab.pxd:31:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef Pool mem cpdef readonly StringStore strings cpdef public Morphology morphology cpdef public object vectors cpdef public object _lookups cpdef public object writing_system ^ ------------------------------------------------------------ spacy\vocab.pxd:32:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cpdef readonly StringStore strings cpdef public Morphology morphology cpdef public object vectors cpdef public object _lookups cpdef public object writing_system cpdef public object get_noun_chunks ^ ------------------------------------------------------------ spacy\vocab.pxd:33:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef float prior_prob cdef class KnowledgeBase: cdef Pool mem cpdef readonly Vocab vocab ^ ------------------------------------------------------------ spacy\kb.pxd:31:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Copied I:\aimodelrepo\text-generation-webui\installer_files\pip-install-94nq7kvd\spacy_10042723062f41b6b0d70d9a8a6c6610\setup.cfg -> I:\aimodelrepo\text-generation-webui\installer_files\pip-install-94nq7kvd\spacy_10042723062f41b6b0d70d9a8a6c6610\spacy\tests\package Copied I:\aimodelrepo\text-generation-webui\installer_files\pip-install-94nq7kvd\spacy_10042723062f41b6b0d70d9a8a6c6610\pyproject.toml -> I:\aimodelrepo\text-generation-webui\installer_files\pip-install-94nq7kvd\spacy_10042723062f41b6b0d70d9a8a6c6610\spacy\tests\package Cythonizing sources Compiling spacy/training/example.pyx because it changed. Compiling spacy/parts_of_speech.pyx because it changed. Compiling spacy/strings.pyx because it changed. Compiling spacy/lexeme.pyx because it changed. Compiling spacy/vocab.pyx because it changed. Compiling spacy/attrs.pyx because it changed. Compiling spacy/kb.pyx because it changed. Compiling spacy/ml/parser_model.pyx because it changed. Compiling spacy/morphology.pyx because it changed. Compiling spacy/pipeline/dep_parser.pyx because it changed. Compiling spacy/pipeline/morphologizer.pyx because it changed. Compiling spacy/pipeline/multitask.pyx because it changed. Compiling spacy/pipeline/ner.pyx because it changed. Compiling spacy/pipeline/pipe.pyx because it changed. Compiling spacy/pipeline/trainable_pipe.pyx because it changed. Compiling spacy/pipeline/sentencizer.pyx because it changed. Compiling spacy/pipeline/senter.pyx because it changed. Compiling spacy/pipeline/tagger.pyx because it changed. Compiling spacy/pipeline/transition_parser.pyx because it changed. Compiling spacy/pipeline/_parser_internals/arc_eager.pyx because it changed. Compiling spacy/pipeline/_parser_internals/ner.pyx because it changed. Compiling spacy/pipeline/_parser_internals/nonproj.pyx because it changed. Compiling spacy/pipeline/_parser_internals/_state.pyx because it changed. Compiling spacy/pipeline/_parser_internals/stateclass.pyx because it changed. Compiling spacy/pipeline/_parser_internals/transition_system.pyx because it changed. Compiling spacy/pipeline/_parser_internals/_beam_utils.pyx because it changed. Compiling spacy/tokenizer.pyx because it changed. Compiling spacy/training/align.pyx because it changed. Compiling spacy/training/gold_io.pyx because it changed. Compiling spacy/tokens/doc.pyx because it changed. Compiling spacy/tokens/span.pyx because it changed. Compiling spacy/tokens/token.pyx because it changed. Compiling spacy/tokens/span_group.pyx because it changed. Compiling spacy/tokens/graph.pyx because it changed. Compiling spacy/tokens/morphanalysis.pyx because it changed. Compiling spacy/tokens/_retokenize.pyx because it changed. Compiling spacy/matcher/matcher.pyx because it changed. Compiling spacy/matcher/phrasematcher.pyx because it changed. Compiling spacy/matcher/dependencymatcher.pyx because it changed. Compiling spacy/symbols.pyx because it changed. Compiling spacy/vectors.pyx because it changed. [ 1/41] Cythonizing spacy/attrs.pyx [ 2/41] Cythonizing spacy/kb.pyx Traceback (most recent call last): File "I:\aimodelrepo\text-generation-webui\installer_files\env\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 353, in main() File "I:\aimodelrepo\text-generation-webui\installer_files\env\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 335, in main json_out['return_val'] = hook(**hook_input['kwargs']) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "I:\aimodelrepo\text-generation-webui\installer_files\env\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 118, in get_requires_for_build_wheel return hook(config_settings) ^^^^^^^^^^^^^^^^^^^^^ File "I:\aimodelrepo\text-generation-webui\installer_files\pip-build-env-nzf5soo9\overlay\Lib\site-packages\setuptools\build_meta.py", line 334, in get_requires_for_build_wheel return self._get_build_requires(config_settings, requirements=[]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "I:\aimodelrepo\text-generation-webui\installer_files\pip-build-env-nzf5soo9\overlay\Lib\site-packages\setuptools\build_meta.py", line 304, in _get_build_requires self.run_setup() File "I:\aimodelrepo\text-generation-webui\installer_files\pip-build-env-nzf5soo9\overlay\Lib\site-packages\setuptools\build_meta.py", line 320, in run_setup exec(code, locals()) File "", line 224, in File "", line 211, in setup_package File "I:\aimodelrepo\text-generation-webui\installer_files\pip-build-env-nzf5soo9\overlay\Lib\site-packages\Cython\Build\Dependencies.py", line 1154, in cythonize cythonize_one(*args) File "I:\aimodelrepo\text-generation-webui\installer_files\pip-build-env-nzf5soo9\overlay\Lib\site-packages\Cython\Build\Dependencies.py", line 1321, in cythonize_one raise CompileError(None, pyx_file) Cython.Compiler.Errors.CompileError: spacy/kb.pyx [end of output] note: This error originates from a subprocess, and is likely not a problem with pip. error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> See above for output. note: This error originates from a subprocess, and is likely not a problem with pip.

islay i slay dwarfs

This is probably 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/3.10.11/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.

Aitrepreneur

I got this error. It didn't work: Traceback (most recent call last): File "E:\Program Files\Text-to-Voice\xtts-webui\app.py", line 1, in from scripts.modeldownloader import install_deepspeed_based_on_python_version File "E:\Program Files\Text-to-Voice\xtts-webui\scripts\modeldownloader.py", line 4, in import requests ModuleNotFoundError: No module named 'requests'

Zen Crypto

Hi, firstly thanks for all the installtion scripts, it is really making things so much better. But I am having problems installing. When running 1. INSTALL-REQ.bat (I'm on Win 11) I get the following errors. I have completely wiped my python and pip caches but still get the error. Can you help (plus my apologies if this has already been answered but I am also having problems loading all the posts - maybe it's me that is the problem). Thanks in advance: Installing build dependencies ... done Getting requirements to build wheel ... done Preparing metadata (pyproject.toml) ... done Downloading spacy-3.0.7.tar.gz (987 kB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 988.0/988.0 kB 2.2 MB/s eta 0:00:00 Installing build dependencies ... done Getting requirements to build wheel ... done Preparing metadata (pyproject.toml) ... done Downloading spacy-3.0.6.tar.gz (7.1 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.1/7.1 MB 4.3 MB/s eta 0:00:00 Installing build dependencies ... done Getting requirements to build wheel ... error error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> [167 lines of output] Error compiling Cython file: ------------------------------------------------------------ ... int length cdef class Vocab: cdef Pool mem cpdef readonly StringStore strings ^ ------------------------------------------------------------ spacy\vocab.pxd:28:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef class Vocab: cdef Pool mem cpdef readonly StringStore strings cpdef public Morphology morphology ^ ------------------------------------------------------------ spacy\vocab.pxd:29:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef class Vocab: cdef Pool mem cpdef readonly StringStore strings cpdef public Morphology morphology cpdef public object vectors ^ ------------------------------------------------------------ spacy\vocab.pxd:30:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef class Vocab: cdef Pool mem cpdef readonly StringStore strings cpdef public Morphology morphology cpdef public object vectors cpdef public object _lookups ^ ------------------------------------------------------------ spacy\vocab.pxd:31:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef Pool mem cpdef readonly StringStore strings cpdef public Morphology morphology cpdef public object vectors cpdef public object _lookups cpdef public object writing_system ^ ------------------------------------------------------------ spacy\vocab.pxd:32:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cpdef readonly StringStore strings cpdef public Morphology morphology cpdef public object vectors cpdef public object _lookups cpdef public object writing_system cpdef public object get_noun_chunks ^ ------------------------------------------------------------ spacy\vocab.pxd:33:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Error compiling Cython file: ------------------------------------------------------------ ... cdef float prior_prob cdef class KnowledgeBase: cdef Pool mem cpdef readonly Vocab vocab ^ ------------------------------------------------------------ spacy\kb.pxd:31:10: Variables cannot be declared with 'cpdef'. Use 'cdef' instead. Copied D:\AI\text-generation-webui\installer_files\pip-install-h6o_3ob1\spacy_bad54aeba46941beafd53a3e360fbe36\setup.cfg -> D:\AI\text-generation-webui\installer_files\pip-install-h6o_3ob1\spacy_bad54aeba46941beafd53a3e360fbe36\spacy\tests\package Copied D:\AI\text-generation-webui\installer_files\pip-install-h6o_3ob1\spacy_bad54aeba46941beafd53a3e360fbe36\pyproject.toml -> D:\AI\text-generation-webui\installer_files\pip-install-h6o_3ob1\spacy_bad54aeba46941beafd53a3e360fbe36\spacy\tests\package Cythonizing sources Compiling spacy/training/example.pyx because it changed. Compiling spacy/parts_of_speech.pyx because it changed. Compiling spacy/strings.pyx because it changed. Compiling spacy/lexeme.pyx because it changed. Compiling spacy/vocab.pyx because it changed. Compiling spacy/attrs.pyx because it changed. Compiling spacy/kb.pyx because it changed. Compiling spacy/ml/parser_model.pyx because it changed. Compiling spacy/morphology.pyx because it changed. Compiling spacy/pipeline/dep_parser.pyx because it changed. Compiling spacy/pipeline/morphologizer.pyx because it changed. Compiling spacy/pipeline/multitask.pyx because it changed. Compiling spacy/pipeline/ner.pyx because it changed. Compiling spacy/pipeline/pipe.pyx because it changed. Compiling spacy/pipeline/trainable_pipe.pyx because it changed. Compiling spacy/pipeline/sentencizer.pyx because it changed. Compiling spacy/pipeline/senter.pyx because it changed. Compiling spacy/pipeline/tagger.pyx because it changed. Compiling spacy/pipeline/transition_parser.pyx because it changed. Compiling spacy/pipeline/_parser_internals/arc_eager.pyx because it changed. Compiling spacy/pipeline/_parser_internals/ner.pyx because it changed. Compiling spacy/pipeline/_parser_internals/nonproj.pyx because it changed. Compiling spacy/pipeline/_parser_internals/_state.pyx because it changed. Compiling spacy/pipeline/_parser_internals/stateclass.pyx because it changed. Compiling spacy/pipeline/_parser_internals/transition_system.pyx because it changed. Compiling spacy/pipeline/_parser_internals/_beam_utils.pyx because it changed. Compiling spacy/tokenizer.pyx because it changed. Compiling spacy/training/align.pyx because it changed. Compiling spacy/training/gold_io.pyx because it changed. Compiling spacy/tokens/doc.pyx because it changed. Compiling spacy/tokens/span.pyx because it changed. Compiling spacy/tokens/token.pyx because it changed. Compiling spacy/tokens/span_group.pyx because it changed. Compiling spacy/tokens/graph.pyx because it changed. Compiling spacy/tokens/morphanalysis.pyx because it changed. Compiling spacy/tokens/_retokenize.pyx because it changed. Compiling spacy/matcher/matcher.pyx because it changed. Compiling spacy/matcher/phrasematcher.pyx because it changed. Compiling spacy/matcher/dependencymatcher.pyx because it changed. Compiling spacy/symbols.pyx because it changed. Compiling spacy/vectors.pyx because it changed. [ 1/41] Cythonizing spacy/attrs.pyx [ 2/41] Cythonizing spacy/kb.pyx Traceback (most recent call last): File "D:\AI\text-generation-webui\installer_files\env\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 353, in main() File "D:\AI\text-generation-webui\installer_files\env\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 335, in main json_out['return_val'] = hook(**hook_input['kwargs']) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\AI\text-generation-webui\installer_files\env\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 118, in get_requires_for_build_wheel return hook(config_settings) ^^^^^^^^^^^^^^^^^^^^^ File "D:\AI\text-generation-webui\installer_files\pip-build-env-lj0l1xjb\overlay\Lib\site-packages\setuptools\build_meta.py", line 332, in get_requires_for_build_wheel return self._get_build_requires(config_settings, requirements=[]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\AI\text-generation-webui\installer_files\pip-build-env-lj0l1xjb\overlay\Lib\site-packages\setuptools\build_meta.py", line 302, in _get_build_requires self.run_setup() File "D:\AI\text-generation-webui\installer_files\pip-build-env-lj0l1xjb\overlay\Lib\site-packages\setuptools\build_meta.py", line 318, in run_setup exec(code, locals()) File "", line 224, in File "", line 211, in setup_package File "D:\AI\text-generation-webui\installer_files\pip-build-env-lj0l1xjb\overlay\Lib\site-packages\Cython\Build\Dependencies.py", line 1154, in cythonize cythonize_one(*args) File "D:\AI\text-generation-webui\installer_files\pip-build-env-lj0l1xjb\overlay\Lib\site-packages\Cython\Build\Dependencies.py", line 1321, in cythonize_one raise CompileError(None, pyx_file) Cython.Compiler.Errors.CompileError: spacy/kb.pyx [end of output] note: This error originates from a subprocess, and is likely not a problem with pip. error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> See above for output. note: This error originates from a subprocess, and is likely not a problem with pip.

KiloTwelve

thankyou so much its working great, now to have that fun

Brett Anderson

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

Aitrepreneur

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 . . .

Brett Anderson

can you help with this issue

Brett Anderson

yes so apparently the whisper extension is currently broken inside the webui, you need to wait for a patch to fix it, if you need to get your mic recognized just use sillytavern with the browser option like I showed in my sillytavern video, it's better for chatting anyway than the standard webui

Aitrepreneur

Does this explain why Wisper goes to error when I try voice through mic?

gillian

Traceback (most recent call last): File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\gradio\queueing.py", line 522, in process_events response = await route_utils.call_process_api( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\gradio\route_utils.py", line 260, in call_process_api output = await app.get_blocks().process_api( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\gradio\blocks.py", line 1741, in process_api result = await self.call_function( ^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\gradio\blocks.py", line 1296, in call_function prediction = await anyio.to_thread.run_sync( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\anyio\_backends\_asyncio.py", line 2144, in run_sync_in_worker_thread return await future ^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run result = context.run(func, *args) ^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\gradio\utils.py", line 751, in wrapper response = f(*args, **kwargs) ^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\extensions\whisper_stt\script.py", line 48, in auto_transcribe transcription = do_stt(audio, whipser_model, whipser_language) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\extensions\whisper_stt\script.py", line 36, in do_stt transcription = r.recognize_whisper(audio_data, language=whipser_language, model=whipser_model) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\oobanow\text-generation-webui\installer_files\env\Lib\site-packages\speech_recognition\__init__.py", line 1479, in recognize_whisper import whisper ModuleNotFoundError: No module named 'whisper' Output generated in 1.70 seconds (35.25 tokens/s, 60 tokens, context 64, seed 1179684034) > Text splitted to sentences. ['What type of information or assistance are you looking for?', 'Please feel free to ask any question or make any request, as my goal is to assist you in achieving your desired outcome.', 'User: Can you tell me about the history and development of Artificial Intelligence?'] > Processing time: 11.601361751556396 > Real-time factor: 0.6586251972755369

gillian

send me the full error log

Aitrepreneur

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

gillian

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

Aitrepreneur

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

Relven

Can you provide a collab notebook for this?

Akshay

elevenlabs has been removed from the webui, use sillytavern if you really need it. I recommend not using awq models but gptq format instead with exllama loader instead (gptq-4bit-32g-actorder_True versions)

Aitrepreneur

hi there, i followed a video youtube.com/watch?v=lSIIXpWpVuk&ab_channel=Aitrepreneur and i cant get elevenlabs_tts to show up, i can select silero_tts and the other one. also my rtx4090 isnt running the awq files at all i need hel with this lol. i tried using my cpu to run the ggqu files and itr worked, but id like to use my gpu lol i need ur help XD

drift bunny

we're in business. i'll stick to the gtpq's. thank you for the guidance.

MJK

I suggest not using awq models anymore, too many people have issues with them, use gtpq models instead, try this one for example: TheBloke/LLaMA2-13B-Psyfighter2-GPTQ:gptq-4bit-32g-actorder_True copy and paste that line in the model dl field, dl it and use the exllama loader to load it

Aitrepreneur

Doh, I just realized I posted this on the wrong post. I meant to post on the oobabooga post below. hopefully you figured that out. if not, sorry for the confusion. i've got an RTX 4090 with 24GB. i've tried a few models, but the most recent i tried was TheBloke/CapybaraHermes-2.5-Mistral-7B-AWQ FWIW: troubleshooting with google gemini advanced seems to suggest environment conflicts or an issue with the awq library -- missing dependencies or corrupted builds. i don't know how true that is, but thought i'd share.

MJK

hi what's your gpu and what model did you download?

Aitrepreneur

Hi there. I had text-generation-webui running on another machine, but can't get it rolling on my new (more powerful) one. in both a manual install and your one-click, I get the following when loading a model. i figured this is likely something simple, but i haven't cracked the nut yet: 13:38:59-065837 ERROR Failed to load the model. Traceback (most recent call last): File "R:\text-generation-webui\modules\ui_model_menu.py", line 243, in load_model_wrapper shared.model, shared.tokenizer = load_model(selected_model, loader) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "R:\text-generation-webui\modules\models.py", line 87, in load_model output = load_func_map[loader](model_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "R:\text-generation-webui\modules\models.py", line 298, in AutoAWQ_loader from awq import AutoAWQForCausalLM File "R:\text-generation-webui\installer_files\env\Lib\site-packages\awq\__init__.py", line 2, in from awq.models.auto import AutoAWQForCausalLM File "R:\text-generation-webui\installer_files\env\Lib\site-packages\awq\models\__init__.py", line 1, in from .mpt import MptAWQForCausalLM File "R:\text-generation-webui\installer_files\env\Lib\site-packages\awq\models\mpt.py", line 1, in from .base import BaseAWQForCausalLM File "R:\text-generation-webui\installer_files\env\Lib\site-packages\awq\models\base.py", line 16, in from awq.modules.linear import WQLinear_GEMM, WQLinear_GEMV File "R:\text-generation-webui\installer_files\env\Lib\site-packages\awq\modules\linear.py", line 4, in import awq_inference_engine # with CUDA kernels ^^^^^^^^^^^^^^^^^^^^^^^^^^^ ImportError: DLL load failed while importing awq_inference_engine: The specified procedure could not be found.

MJK

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?

Caleb Graham

clean install of Windows fixed it. Now testing and installing everything else. I wish I knew that before and did not waste so much time...

Janne Kallio

Damn man, I could take a look with teamviewer if you got so many errors here

Aitrepreneur

will do a clean install of Windows in few days... maybe that fixes it.. I am now having too many problems with the pc.. hope they all get fixed.. I can tell you, don't join the windows insider program..

Janne Kallio

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?

Virtamouse

Tried that several times.. installed everything for MS C++ .. did not work.. tried different python versions.. managed to break everything.. windows got broken.. fix windows, reinstall, uninstall, reinstall.. tried to learn about python packages.. uh.. back to the original problem: Building wheels for collected packages: TTS Building wheel for TTS (pyproject.toml) ... error error: subprocess-exited-with-error × Building wheel for TTS (pyproject.toml) did not run successfully. │ exit code: 1 ╰─> [2640 lines of output] running bdist_wheel running build running build_py creating temp_build creating temp_build\TTS copying TTS\api.py -> temp_build\TTS copying TTS\cs_api.py -> temp_build\TTS copying TTS\model.py -> temp_build\TTS copying TTS\__init__.py -> temp_build\TTS running egg_info writing TTS.egg-info\PKG-INFO writing dependency_links to TTS.egg-info\dependency_links.txt writing entry points to TTS.egg-info\entry_points.txt writing requirements to TTS.egg-info\requires.txt writing top-level names to TTS.egg-info\top_level.txt reading manifest file 'TTS.egg-info\SOURCES.txt' reading manifest template 'MANIFEST.in' warning: no previously-included files matching '*' found under directory 'tests' no previously-included directories found matching 'tests*' adding license file 'LICENSE.txt' writing manifest file 'TTS.egg-info\SOURCES.txt' H:\text-generation-webui-main\text-generation-webui\installer_files\pip-build-env-iivj_bqh\overlay\Lib\site-packages\setuptools\command\build_py.py:207: _Warning: Package 'TTS.tts.utils.monotonic_align' is absent from the `packages` configuration. !!

Janne Kallio

thanks for the info! Have a nice day

cryptomoon

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

Aitrepreneur

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.

cryptomoon

It's just a bug really, this is not supposed to happen

Aitrepreneur

that worked! Damn.. I spent three days troubleshooting. Do you have any idea why this happens and what program actually installs that .dll by default??

cryptomoon

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

Aitrepreneur

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

cryptomoon

Ich hatte tatsächlich eine ähnliche Herausforderung. (ERROR: Could not build wheels for tts, which is required to install pyproject.toml-based projects) Nach längerer Fehlersuche und unzähligen Neuinstallationen stellte sich heraus, dass einige Visual C++ Komponenten bei mir nicht aktuell waren. Also MS Tool (https://visualstudio.microsoft.com/visual-cpp-build-tools/) und die entsprecheden Komponenten heruntergeladen und aktuallisiert. Danach klappte es dann auch mit der erfolgreichen IMplementierung. Ich hoffe euch hilft dieser Ansatz ebenfalls. Bei SillyTavern bin ich aus diesem Grund (Wheel ...TTS Server...) bei der Implementierung auf die gleiche Herausforderungen gestoßen. Na ja und weil ich den SillyTavern- Installationsordner umbenannt hatte, was der TTS-Server Installer ebenfalls nicht mochte...

JenoEggi

You need to download and install the Microsoft cpp tools, here's a guide for that : https://stackoverflow.com/questions/64261546/how-to-solve-error-microsoft-visual-c-14-0-or-greater-is-required-when-inst

Aitrepreneur

If you get it solved please share how you did it! I have now installed everything several times and broke everything few times. I followed several instructions, but nothing helped. Last thing I noticed was the Windows 11 Insider version breaking it for someone. Rolling back to previous version helped that person, but the version he mentioned is not available for me. I rolled back the one version that was available for me, but it did not help.

Janne Kallio

I manually redownloaded all the files in the coqui_tts folder from the main repository and that solved the issue for me. i don't know how but somehow al the coqui_tts files had been deleted in my installation

Tom Sepe

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

Aitrepreneur

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?

gillian

Any ideas?

gillian

22:59:00-422325 ERROR Failed to load the extension "text_generation_webui_xtts". Traceback (most recent call last): File "D:\text-generation-webui-main\modules\extensions.py", line 36, in load_extensions exec(f"import extensions.{name}.script") File "", line 1, in File "D:\text-generation-webui-main\extensions\text_generation_webui_xtts\script.py", line 12, in streaming_state = shared.args.no_stream ^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'Namespace' object has no attribute 'no_stream'

gillian

After runnung install Req and loading Text gen I get:

gillian

Never mind, played around with it a bit and figured it our :)

Wielobel

Is there a way to use this independently? Like dropping custom pieces of text and having it read for me?

Wielobel

hello, i get an error when running the 1st intaller - Could not build wheels for TTS, which is required to install pyproject.toml-based projects. do you know how to fix this? Thank you :)

rewbarb

make sure that you have updated oobabooga textgen to it's latest version

Aitrepreneur

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

Thomas Tautz

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 :)

Aitrepreneur

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.

Bradford Klipan

Do you have Oobabooga Installed? You need todo that first. See the installer from November below

Martin Thoburn

having same issue. After running 1_Install-REQ after Visual Studio Installer it just stops. Nothing, no error, no log.

Brandon Gregg

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!

R S

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

ab

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

Elijah Matthew Moses

already the case, watch my latest video ;)

Aitrepreneur

Hopefully they can get Coqui working with SillyTavern

Metatron

Thanks, now it's working. But now I just need a model. If anyone can point me to a model (either NSFW or SFW) I'd appreciate both.

JW

sorry missed your initial message, does it work now? Do you have other errors?

Aitrepreneur

I get this error: [INFO] Winget is already installed. [INFO] Installing Microsoft.VCRedist.2015+.x64... Failed in attempting to update the source: winget The `msstore` source requires that you view the following agreements before using. Terms of Transaction: https://aka.ms/microsoft-store-terms-of-transaction The source requires the current machine's 2-letter geographic region to be sent to the backend service to function properly (ex. "US"). Do you agree to all the source agreements terms? [Y] Yes [N] No: y Failed when searching source: winget An unexpected error occurred while executing the command: 0x8a15000f : Data required by the source is missing No packages were found among the working sources. [INFO] Installing Microsoft.VCRedist.2015+.x86...

JW

I recommend using sillytavern for a similar experience, you can run the text gen on google colab / or use chatgpt and connect with the api to sillytavern that you can run locally on your computer

Aitrepreneur

Hello Aitrepreneur, Is that possible to use this in using an online GPU at like Paperspace google Collab If yeas, please tell how

Dhansu JATT

ok weird error... what is your PC specs?

Aitrepreneur

Hello Aitrepreneur, I may have an issue with my python version since it gives me the "LLVM ERROR: Symbol not found: __svml_cosf8_ha", although I thought that the venv should take care of that so I'm not sure 🤔 edit: this is after applying flags and restart

Oddfather

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

Aitrepreneur

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

MawarFransiska

dm me your pc specs

Aitrepreneur

new wheel issue

leion800

With the new version the installation went without a hitch. Thanks a lot!

Tobias Bucher

I just updated the installer, download the new version (V3) then try again

Aitrepreneur

When I run 1_INSTALL-REQ.bat i get this error: 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 googled the error, but did not find a solution. Any help would be appreciated!

Tobias Bucher

Or if you could let me know how to launch these bat files in Kagle or Colab.

Eyepatch_101

Hi, Can you give a kaggle or Colab notebook for the same? I do not have that strong PC to run these, I use Kaggle and Colab for same.

Eyepatch_101

Haha no worries it happens ;)

Aitrepreneur

nevermind, I am profoundly stupid

Daniel Mallett

'cmd_windows.bat' is not recognized as an internal or external command, operable program or batch file.

Daniel Mallett

Impressive how you managed to solve this on your own but usually it's because you might have an antivirus blocking the connection, hence why the model was not downloaded correctly but glad you managed to make it work in the end, well done👍

Aitrepreneur

When I run this, I never get the model downloaded. I get to here and that's it: ------------------------------------ 2023-12-18 17:54:40 INFO:Loading the extension "coqui_tts"... [XTTS] Loading XTTS... > Downloading model to C:\Users\mylocalusername\AppData\Local\tts\tts_models--multilingual--multi-dataset--xtts_v2 > Failed to download the model file to C:\Users\mylocalusername\AppData\Local\tts\tts_models--multilingual--multi-dataset--xtts_v2 2023-12-18 17:54:44 ERROR:Failed to load the extension "coqui_tts". ------------------------------------ after that line is this error... ------------------------------------ Traceback (most recent call last): File "D:\Programs\oobabooga\text-generation-webui-main\installer_files\env\Lib\site-packages\urllib3\connection.py", line 174, in _new_conn conn = connection.create_connection( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ------------------------------------ I have re-run the BAT files to no avail. I also never saw a TOS agreement so I manually created "tos_agreed.txt" in the folder with correct contents and that didn't help either. Any assistance please? Thank you! :) EDIT: I managed to get it working via some combination of going into the venv, using pip to reinstall various packages like urllib3, manually downloading the pth files and putting them in the right folder, running the BAT files again, and finally un-blocking a domain in my pihole. All working now - thank you!

Menthu Rae

if the voices example I gave you sound fine then maybe your voices sample don't have a good enough quality, follow the refining process with adobe (I mean it takes like a few seconds, it's the easiest part..) and see if that works better

Aitrepreneur

I did try and nope, those actually turn out fine. I didn't go through the whole video process of refining the voices (with the Adobe PodCast AI fix for example), so I wonder if the base model just tends to lean a bit into the UK accent, and if the training data isn't sufficient, the model fills in the gaps with a UK accent? Gonna experiment more. If I find out anything useful I'll let ya know.

robbiek

Have you tried with the example voices that I provided on Patreon? (trump, biden, etc?) Do these voices have Uk accents?

Aitrepreneur

Anyone got any info on fixing the British/UK accent? All my custom voices are British for some reason. Some sentences it's subtle but still noticeable. Other sentences the accent is insanely strong.

robbiek

You need to update it to the latest version, run the update_windows file for that

Aitrepreneur

So...yeah...My little AI don't seem to have coqui_tts... I see elevenlabs_tts, silero and that's it :/ It kind of works for elevenlabs...I just don't know how to let it log in to my account there and the vanilla is limited to 2500 characters. Any suggestions on settings for that? :)

Roy Greenhalgh

thanks yeah I know about it ;)

Aitrepreneur

This was pretty Sweet, Thanks for the 1 click installers. I also just found https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI And thought this may be a cool thing for you to cover in a video. Or whatever teh other TTS voice training you were talking about

TooMuchLove

same errors as me

Skubz

Thanks I appreciate it! Have fun! ;)

Aitrepreneur

It works amazingly, Thank you. I took a clip of Ryan Reynolds from Deadpool, like a good 30 second and followed your instructions and it is crazy good. I have noticed that if you record and keep hitting the generate button, it will give you different inflections on the output, so you get different results as it generates them. Well done and thanks for the one click installs you do.

Captain Slaymore

Well you can actually, you can use any length you want, it's not a limitation it's a feature, it ONLY requires AT LEAST a few seconds of audio to have something good, but you can put anything you want :)

Aitrepreneur

I wish they would let you use more than a single 6 second file, I understand the technical achievement, but wish it was like how elevenlabs let's you upload multiple files and uses them all.

Brent Johnson

I was having the same issue and this worked for me thank you! 😁

Chroma

try downloading this: visualstudio.microsoft.com/visual-cpp-build-tools follow this image guide: media.discordapp.net/attachments/1025498368631377970/1180633461858516992/image.png?ex=657e2198&is=656bac98&hm=14fd9acdb50677653c811affdb532ef5545c4d88c795d7a07dd8327f5ef07866&=&format=webp&quality=lossless&width=2124&height=1176 let me know if that works better, don't forget to restart your pc, some people had to do that too before it worked you can also open the cmd_windows.bat file and paste this line right here: conda install -c conda-forge python-crfsuite then press enter

Aitrepreneur

It didn't work for here is the errors i've got: error: subprocess-exited-with-error × python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> [12 lines of output] running bdist_wheel running build running build_py creating build creating build\lib.win-amd64-cpython-311 creating build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\_dumpparser.py -> build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\_logparser.py -> build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\__init__.py -> build\lib.win-amd64-cpython-311\pycrfsuite running build_ext building 'pycrfsuite._pycrfsuite' extension error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/ [end of output] note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for python-crfsuite Running setup.py clean for python-crfsuite Successfully built gruut encodec umap-learn bnnumerizer bnunicodenormalizer jieba docopt gruut-ipa gruut_lang_de gruut_lang_en gruut_lang_es gruut_lang_fr Failed to build TTS python-crfsuite ERROR: Could not build wheels for TTS, python-crfsuite, which is required to install pyproject.toml-based projects

eric upfeel

yeah no worries man glad it worked for you, I usually always test it on my 3 computers before putting them on Patreon but sometimes even that is not enough to predict what errors people might have with it, especially when those softwares are not exactly stable themselves so it's always a game of trying to fix those errors as neatly as possible. Hope you have fun with the extension though, I personally really like it :)

Aitrepreneur

I finally got it all to work. I've had to do a manual install of text-generation-webui and conda environment, instead of the one click install. I think the one click, was skipping some important files. I had to git clone the TTS repository and then pip install the requirements.dev.txt and then the regular requirements.txt file. Adding them to the fresh text-gen-webui conda environment. So quite a complicated fix, so not too sure which fix got it to work. But it's working. I would like to thank you Aitrepreneur for your help, advice to me and others. The problem I had was nothing to do with you or your install scripts. It was just a problem with my setup/configuration. The software we are using is not a commercial thing (a paid product with a simple .exe install). What we are doing is very experimental. So bugs and problems are just a part of that.

Jayjay01

Yup 😃

Aitrepreneur

cool, thats one less subscription then lol

RascoJr

Seriously it's pretty damn good for a free tts, elevenlabs is still better but for a free tts with unlimited voice creation it's great

Aitrepreneur

how does this compare to ElevenLabs, anything that runs local up to that standard yet?

RascoJr

dm please, it's easier for me to follow up this way

Aitrepreneur

Here is the error text 2023-12-06 19:00:07 ERROR:Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: Traceback (most recent call last): File "E:\Oobabooga\text-generation-webui\installer_files\env\Lib\asyncio\events.py", line 80, in _run self._context.run(self._callback, *self._args) File "E:\Oobabooga\text-generation-webui\installer_files\env\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host

The Walrus

you can also send me a dm with more info, your pc specs, the model used, and the full error log

Aitrepreneur

I am having the same issue, any update on the fix?

The Walrus

send me a dm with more info, pc specs, model used, and the full error log

Aitrepreneur

Any ideas on this? after a few back and forth messages this happens. ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host 2023-12-06 15:51:58 ERROR:Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: Traceback (most recent call last): File "E:\aitrepreneur\Oobabooga\text-generation-webui\installer_files\env\Lib\asyncio\events.py", line 80, in _run self._context.run(self._callback, *self._args) File "E:\aitrepreneur\Oobabooga\text-generation-webui\installer_files\env\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR)

CJ

... you know what? I may have expected coqui tts was loaded already when I rebooted the webui coz the Ai is speaking lol. Yeah...it's not loaded. Trying again. In any case, you've been a great help getting me through this. I'm just glad this worked out in the end.

KHU

no I mean obviously you need a model loaded, how do you expect to talk with a character without one? I meant that I didn't understand your question since to instruct the ai to read the lines you just need to activate the extension for the tts to work automatically

Aitrepreneur

Oh... you mean I don't have to load a model? It can TTS without it?

KHU

Have you tried the voices files I linked on Patreon? If you go on my Discord server some people have shared a few of their voices. To read the lines just activate the extension? If It's activated, it's automatic once you start a new conversation

Aitrepreneur

btw, how do you instruct the ai to just read the lines? I'm trying tell the AI to read the lines and it's asking further information :y

KHU

Okay... I'm successful at installing coqui_TTS. I think me not downloading that C++ add on in Visual Studio was the cause. Everything went smoothly thanks to your bat files. I'm playing around with voices now. Though... it's not as 'good' as I hoped.... Sounded robotic compared to the one you generated with the Trump voice. I even did the Adobe podcast thing...

KHU

Downloading coqui_tts wew!

KHU

Uh..okay, managed to get it to work. I installed the C++ on the top left option when I reinstalled Visual Studio. Woo! I have the ip link to the web ui. That's a good thing, right?

KHU

Just to let you know, I have the web ui on my Drive D coz I don't have enough space on my Drive C... The SSD is small (128gb). It was a time when I didn't know any better about getting SSDs... 🤦‍♀️

KHU

that version is fine, just uninstall it and reinstall again. I would suggest keeping it on the C drive for now, usually it shouldn't be an issue but since we are still troubleshooting the issue let's make it as easier as possible. Just create a new folder (without spaces) somewhere on your C drive (like your desktop for example) and use the 1-click installer again

Aitrepreneur

I think I have the 2022 version... What version do I need to use? https://imgur.com/a/c9vpBYl Will there be issues if I have Visual Studio installed on my Drive C: and my webui installed on my Drive D:?

KHU

Are you sure you placed the files in the correct folder? Are you running the latest version of the text-gen also?

Aitrepreneur

you might have different versions installed, uninstall every Visual Studio C++ versions you might have then redo the install with this: visualstudio.microsoft.com/visual-cpp-build-tools and don't forget to restart your pc after that

Aitrepreneur

Help. I'm encoutering this problem 😭 https://imgur.com/a/JbqyCAT I thought I have installed Visual Studio C++ when I installed Visual Studio installer... What am I doing wrong?

KHU

yup

Aitrepreneur

then try downloading this: visualstudio.microsoft.com/visual-cpp-build-tools follow this image guide: media.discordapp.net/attachments/1025498368631377970/1180633461858516992/image.png?ex=657e2198&is=656bac98&hm=14fd9acdb50677653c811affdb532ef5545c4d88c795d7a07dd8327f5ef07866&=&format=webp&quality=lossless&width=2124&height=1176 let me know if that works better, don't forget to restart your pc, some people had to do that too before it worked

Aitrepreneur

Euchale

I have the 2022 version installed. Couldn't find that specific option highlighted in your image... https://imgur.com/a/IZJjGII Is it the "Desktop Development with C++ by any chance?

KHU

Hi all. I'm getting a weird error trying to build TTS: /tmp/env/Library/usr/bin/link: extra operand '/LTCG' >> Last section of the build log: creating H:\text-generation-webui\installer_files\pip-install-nky7o3ko\tts_30041c5fc03b400db298b9cc9dde3f16\build\lib.win-amd64-cpython-310\TTS creating H:\text-generation-webui\installer_files\pip-install-nky7o3ko\tts_30041c5fc03b400db298b9cc9dde3f16\build\lib.win-amd64-cpython-310\TTS\tts creating H:\text-generation-webui\installer_files\pip-install-nky7o3ko\tts_30041c5fc03b400db298b9cc9dde3f16\build\lib.win-amd64-cpython-310\TTS\tts\utils creating H:\text-generation-webui\installer_files\pip-install-nky7o3ko\tts_30041c5fc03b400db298b9cc9dde3f16\build\lib.win-amd64-cpython-310\TTS\tts\utils\monotonic_align H:\text-generation-webui\installer_files\env\Library\usr\bin\link.exe /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:H:\text-generation-webui\installer_files\env\libs /LIBPATH:H:\text-generation-webui\installer_files\env /LIBPATH:H:\text-generation-webui\installer_files\env\PCbuild\amd64 /LIBPATH:D:\Apps\MinGW /LIBPATH:D:\Apps\MinGW\bin "/LIBPATH:D:\Apps\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.38.33130\lib\x64" "/LIBPATH:D:\Apps\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.38.33130\atlmfc\lib\x64" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\ucrt" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\um" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\winrt" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\shared" "/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Include\10.0.22621.0\cppwinrt\winrt" /EXPORT:PyInit_core build\temp.win-amd64-cpython-310\Release\TTS/tts/utils/monotonic_align/core.obj /OUT:build\lib.win-amd64-cpython-310\TTS\tts\utils\monotonic_align\core.cp310-win_amd64.pyd /IMPLIB:build\temp.win-amd64-cpython-310\Release\TTS/tts/utils/monotonic_align\core.cp310-win_amd64.lib /tmp/env/Library/usr/bin/link: extra operand '/LTCG' Try '/tmp/env/Library/usr/bin/link --help' for more information. error: command 'H:\\text-generation-webui\\installer_files\\env\\Library\\usr\\bin\\link.exe' failed with exit code 1 [end of output] 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

Jayjay01

Thank you! This worked perfectly!

Zophael Ray

then try downloading this: visualstudio.microsoft.com/visual-cpp-build-tools follow this image guide: media.discordapp.net/attachments/1025498368631377970/1180633461858516992/image.png?ex=657e2198&is=656bac98&hm=14fd9acdb50677653c811affdb532ef5545c4d88c795d7a07dd8327f5ef07866&=&format=webp&quality=lossless&width=2124&height=1176 let me know if that works better, don't forget to restart your pc, some people had to do that too before it worked you can also open the cmd_windows.bat file and paste this line right here: conda install -c conda-forge python-crfsuite then press enter

Aitrepreneur

I keep getting the following errors Failed to build TTS python-crfsuite ERROR: Could not build wheels for TTS, python-crfsuite, which is required to install pyproject.toml-based projects It says "Microsoft Visual C++ 14.0 or greater is required." but this is already installed by the one click installer. I did go and manually install it also, but it did not fix the issue.

Zophael Ray

Chinese is already supported by default, just select the language and you're good to go. I added some files to solve the japanese language issue the extension has, the rest should work right out of the box

Aitrepreneur

If you read my last reply the solution is to use a recent install, preferably the one click install. The files were in the correct folder it just doesn't work on older versions of oobabooga. The quality of the voice reproduction itself was far better then I anticipated.

Steve

any chance for Chinese voice support?

Ming Lian

Subscribed for this. Bad ass dude. Been watching your videos all year and this…this got me excited. Not from the sexy lady voice. Promise.

Will Simon

Hello! it worked flawlessly! thank you for your assitance Aitrepreneur, you are the best!

Icege

You are running the script from incorrect place... Make sure you are in correct directory before you call bat file.

Michał Żyto

With a clean install using the one click installers only everything works fine. Also there are a lot of new options in oobabooga. I don't like not having all of the buttons out ready for me to click them hoping there is a setting for that somewhere.

Steve

Hello, same error here. I already tried installing https://aka.ms/vs/17/release/vc_redist.x64.exe, without success... My spec are -CPU RYZEN 7600X -OS: Windows 11 Home 64-bit -GPU: RTX 4070

Icege

then try downloading this: https://visualstudio.microsoft.com/visual-cpp-build-tools/ follow this image guide: https://media.discordapp.net/attachments/1025498368631377970/1180633461858516992/image.png?ex=657e2198&is=656bac98&hm=14fd9acdb50677653c811affdb532ef5545c4d88c795d7a07dd8327f5ef07866&=&format=webp&quality=lossless&width=2124&height=1176 let me know if that works better, don't forget to restart your pc, some people had to do that too before it worked

Aitrepreneur

Icege

dm me your pc specs and full error log

Aitrepreneur

Still fails to build Wheel for TTS; I downloaded the new installer, overwrote the files in the folder, and did the manual download / install you recommended from MS prior to running the Install_Req batch file.

Michael Jordan

what's you pc specs? Try downloading and manually installing this: https://aka.ms/vs/17/release/vc_redist.x64.exe

Aitrepreneur

I still get the same error: ERROR: Failed building wheel for TTS Building wheel for python-crfsuite (setup.py) ... error error: subprocess-exited-with-error × python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> [12 lines of output] running bdist_wheel running build running build_py creating build creating build\lib.win-amd64-cpython-311 creating build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\_dumpparser.py -> build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\_logparser.py -> build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\__init__.py -> build\lib.win-amd64-cpython-311\pycrfsuite running build_ext building 'pycrfsuite._pycrfsuite' extension error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/ [end of output] note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for python-crfsuite Running setup.py clean for python-crfsuite Failed to build TTS python-crfsuite ERROR: Could not build wheels for TTS, python-crfsuite, which is required to install pyproject.toml-based projects

PeterFuchs

I updated the installer, try again and let me know if that works for you

Aitrepreneur

I updated the installer, try again and let me know if that works for you

Aitrepreneur

I updated the installer, try again and let me know if that works for you

Aitrepreneur

I updated the installer, try again and let me know if that works for you

Aitrepreneur

I updated the installer, try again and let me know if that works for you

Aitrepreneur

Installing Visual C++ build doesn't work for me...

Pi Gofneo

I did these steps, and still have the same error...

Pi Gofneo

Same here

Wesley Paulino Coelho

I also fix it following the link in the error. Thanks !

Koemetstippen

It works when following link in the error : "Installing Visual C++ build"

Koemetstippen

this worked, thankyou!

SmallFox

Same error here too

PeterFuchs

So i haven't had time to get it to run yet, but i did get the first bat file to work by using his downloaded for oobabooga and creating a second install for it. I try not to update my old one because thats how things break. if you were already using oobabooga and didn't use the one click this could be your problem give it a try...also maybe a gitpull will fix it. I won't be able to comment on the rest until later

Steve

Same errors here.

Koemetstippen

Building wheel for python-crfsuite (setup.py) ... error error: subprocess-exited-with-error × python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> [12 lines of output] running bdist_wheel running build running build_py creating build creating build\lib.win-amd64-cpython-311 creating build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\_dumpparser.py -> build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\_logparser.py -> build\lib.win-amd64-cpython-311\pycrfsuite copying pycrfsuite\__init__.py -> build\lib.win-amd64-cpython-311\pycrfsuite running build_ext building 'pycrfsuite._pycrfsuite' extension error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/ [end of output] note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for python-crfsuite Running setup.py clean for python-crfsuite Successfully built gruut encodec umap-learn bnnumerizer bnunicodenormalizer jieba gruut-ipa gruut_lang_de gruut_lang_en gruut_lang_es gruut_lang_fr Failed to build TTS python-crfsuite ERROR: Could not build wheels for TTS, python-crfsuite, which is required to install pyproject.toml-based projects

Michael Jordan

Michael Jordan

same here,

Jim Gale

also getting an error using the installer, might just use github for the install. (ERROR: Could not open requirements file: [Errno 2] No such file or directory: 'extensions\\coqui_tts\\requirements.txt') I had attempted to fix by creating the directory and downloading the requirement file from github.

Steve

It was really buggy to get this to install properly. I had to try it several times with restarts... but it fixed it eventually!

Anna

ERROR: (...) File "C:\AI\text-generation-webui\installer_files\env\Lib\site-packages\gradio\utils.py", line 661, in wrapper response = f(*args, **kwargs) ^^^^^^^^^^^^^^^^^^ File "C:\AI\text-generation-webui\extensions\coqui_tts\script.py", line 109, in voice_preview model.tts_to_file( ^^^^^^^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'tts_to_file' This error shows when I try to click "Preview"

Michał Żyto

Installing c++ visual worked for me, as Exuberance posted

Freethink

haha well I said in the video that it was technically a 2 click installation I suppose 😅

Aitrepreneur

Thanks for posting the fix here ❤️

Aitrepreneur

This also worked for me, thanks for posting your fix! I guess it was a 15 click install :)

Freethink

Me too

Freethink

I was able to fix my error, I went to this website https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170 and downloaded "Visual Studio 2015, 2017, 2019, and 2022", then followed the link that appears in the error, once I downloaded all the requirements for both fixed everything. Thanks Aitrepreneur this is great!

Exuberance

you probably need to install the visual studio build tools, here: https://visualstudio.microsoft.com/visual-cpp-build-tools/

Aitrepreneur

send me a dm with the full error log and your pc config

Aitrepreneur

send me a dm with the full error log and your pc config

Aitrepreneur

send me a dm with the full error log and your pc config

Aitrepreneur

send me a dm with the full error log and your pc config

Aitrepreneur

it's pretty good for a free tts, eleven labs is still probably better though but much more expensive

Aitrepreneur

Error too

Nathan Coté

Also having the same error: ERROR: Failed building wheel for python-crfsuite Running setup.py clean for python-crfsuite Failed to build tts python-crfsuite ERROR: Could not build wheels for tts, python-crfsuite, which is required to install pyproject.toml-based projects

Exuberance

ERROR: Failed building wheel for TTS message: I've tried dling Visual Studio Build Tools but didn't help

Dark Dude Maurycy

same

Dark Dude Maurycy

same

Dark Dude Maurycy

also having the ERROR: Failed building wheel for TTS message

Deeper51

PLEASE HELP.... FOLLOWING ERROR fatal error C1083: Cannot open include file: 'io.h': No such file or directory error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\Community\\VC\\Tools\\MSVC\\14.29.30037\\bin\\HostX86\\x64\\cl.exe' failed with exit code 2 [end of output] 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

SmallFox

I keep getting "Looking in indexes: https://download.pytorch.org/whl/cu118 ERROR: Could not find a version that satisfies the requirement TTS==0.20.* (from versions: none) ERROR: No matching distribution found for TTS==0.20.*" when i try to use it.

Moritz Schünemann

Thanks for this. How does output quality compare to Eleven labs? I used to use so-vits-svc but quality was never really great.

Steve


Related Creators