After finetune model - An error occurred: `penalty` has to be a strictly positive float, but is 7.0

[IHaveAGenericUserName]

After fine-tuning a model I receive an error when I try to generate new TTS regardless of if I use the newly trained model or not.

An error occurred: penalty has to be a strictly positive float, but is 7.0 ERROR: Exception in ASGI application

To Reproduce

• Install alltalk standalone, run start_alltalk.bat, verify it works to generate TTS.
• Exit alltalk, run start_finetune.bat
• Follow prompts to tune model, test model, compress and move model to a folder
• Exit finetune, run alltalk again
• Try to produce any tts and receive error.
• Reinstall alltalk in new directory, works fine. Move trained models over, works fine.

• Screenshots

Text/logs `[AllTalk Model] Ready [AllTalk TTSGen] Using API Local

Text splitted to sentences. ['AllTalk is a labour of love, developed and supported in my personal free time.', 'As such, my ability to respond to support requests is limited.', 'I prioritize issues based on their impact and the number of users affected.'] An error occurred: penalty has to be a strictly positive float, but is 7.0 ERROR: Exception in ASGI application Traceback (most recent call last): File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\responses.py", line 326, in call stat_result = await anyio.to_thread.run_sync(os.stat, self.path) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\anyio_backends_asyncio.py", line 2144, in run_sync_in_worker_thread return await future ^^^^^^^^^^^^ File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\anyio_backends_asyncio.py", line 851, in run result = context.run(func, *args) ^^^^^^^^^^^^^^^^^^^^^^^^ FileNotFoundError: [WinError 2] The system cannot find the file specified: 'L:\LLMs\AllTalk\alltalk_tts\outputs\undefined'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\uvicorn\protocols\http\h11_impl.py", line 407, in run_asgi result = await app( # type: ignore[func-returns-value] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\uvicorn\middleware\proxy_headers.py", line 69, in call return await self.app(scope, receive, send) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\fastapi\applications.py", line 1054, in call await super().call(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\applications.py", line 123, in call await self.middleware_stack(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\middleware\errors.py", line 186, in call raise exc File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\middleware\errors.py", line 164, in call await self.app(scope, receive, _send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\middleware\cors.py", line 83, in call await self.app(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\middleware\exceptions.py", line 62, in call await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette_exception_handler.py", line 64, in wrapped_app raise exc File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\routing.py", line 758, in call await self.middleware_stack(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\routing.py", line 778, in app await route.handle(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\routing.py", line 299, in handle await self.app(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\routing.py", line 79, in app await wrap_app_handling_exceptions(app, request)(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette_exception_handler.py", line 64, in wrapped_app raise exc File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\routing.py", line 77, in app await response(scope, receive, send) File "L:\LLMs\AllTalk\alltalk_tts\alltalk_environment\env\Lib\site-packages\starlette\responses.py", line 329, in call raise RuntimeError(f"File at path {self.path} does not exist.") RuntimeError: File at path L:\LLMs\AllTalk\alltalk_tts\outputs\undefined does not exist.`

Desktop (please complete the following information): AllTalk was updated: Fresh install today Custom Python environment: No Text-generation-webUI was updated: today

[erew123]

Hi @IHaveAGenericUserName

All fixed. Looks like the most recent version(s) of Transformers is demanding a float value.

If you git pull the update https://github.com/erew123/alltalk_tts#-updating (no need to re apply the requirements), it should now for you.

BTW, you will get very slow generation using API Local, vs XTTS Local w/ DeepSpeed enabled.

Thanks