[GH-ISSUE #18878] issue: Text To Speech Fails because of CVE-2025-32434 pytorch updates #34231

New Issue

Closed

opened 2026-04-25 08:08:20 -05:00 by GiteaMirror · 1 comment

GiteaMirror commented 2026-04-25 08:08:20 -05:00

Owner

Copy Link

Copy Source

Originally created by @MAWK0235 on GitHub (Nov 3, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18878

Check Existing Issues

• I have searched for any existing and/or related issues.
• I have searched for any existing and/or related discussions.
• I am using the latest version of Open WebUI.

Installation Method

Pip Install

Open WebUI Version

v0.6.34

Ollama Version (if applicable)

0.12.3

Operating System

Ubuntu 24.04.3 LTS

Browser (if applicable)

Firefox

Confirmation

• I have read and followed all instructions in README.md.
• I am using the latest version of both Open WebUI and Ollama.
• I have included the browser console logs.
• I have included the Docker container logs.
• I have provided every relevant configuration, setting, and environment variable used in my setup.
• I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
• I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
• Start with the initial platform/version/OS and dependencies used,
• Specify exact install/launch/configure commands,
• List URLs visited, user input (incl. example values/emails/passwords if needed),
• Describe all options and toggles enabled or changed,
• Include any files or environmental changes,
• Identify the expected and actual result at each stage,
• Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

click the TTS button and receive a vocal reading of a response

Actual Behavior

Currently, using the "tts-1" text-to-speech engine triggers an infinite loop when a user activates the text-to-speech functionality. This is due to a recent change in PyTorch. PyTorch v2.6 or higher is now required to load the model used by tts-1 due to a security vulnerability. The error message received is: "ValueError: Due to a serious vulnerability issue in torch.load, even with weights_only=True, we now require users to upgrade torch to at least v2.6 in order to use the function. This version restriction does not apply when loading files with safetensors."

Resolution: Upgrade the PyTorch installation to version 2.6 or later. Consider migrating the model to a safetensors format to avoid this restriction in the future. (See attached logs for details.)

Steps to Reproduce

Steps to Reproduce: TTS-1 Text-to-Speech Failure

Step 1: Configure Text-to-Speech to "tts-1"

1. Navigate to the application's "Text-to-Speech" settings
2. Select "tts-1" as the active text-to-speech engine.
3. Save the changes to the settings.

Step 2: Query the LLM

1. Using the application's interface, formulate a question or prompt for the integrated Large Language Model. (Example: "Tell me a short story about a cat.")
2. Submit the prompt to the LLM.
3. Wait for the LLM to generate a response. Verify the LLM response is appearing in the application.

Step 3: Monitor Logs (Pre-Failure)

1. Open the application's log file or logging console. (Specify the location of the log file).
2. Observe the logs for any initial messages related to the LLM response or TTS engine initialization. (This is to confirm the application is starting up normally). You should see logs showing the LLM response being received.

Step 4: Activate Text-to-Speech and Monitor Failure

1. Locate the "Text-to-Speech" button or control associated with the LLM’s response.
2. Click the "Text-to-Speech" button.
3. Monitor the application’s behavior and the logs immediately after clicking the button.

Expected Result/Failure:

• The application will likely enter a loop, becoming unresponsive or freezing.
• The logs will display the ValueError related to the PyTorch version requirement. The error message should be similar to this:

  ValueError: Due to a serious vulnerability issue in `torch.load`, even with `weights_only=True`, we now require users to upgrade torch to at least v2.6 in order to use the function. This version restriction does not apply when loading files with safetensors.
  

• You may observe repeated error messages in the logs related to loading the PyTorch model.

Logs & Screenshots

Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: 2025-11-03 02:20:09.194 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 192.168.1.14:0 - "POST /api/v1/audio/speech HTTP/1.1" 500
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: Exception in ASGI application
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: + Exception Group Traceback (most recent call last):
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 79, in collapse_excgroups
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | yield
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 183, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | async with anyio.create_task_group() as task_group:
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/anyio/_backends/_asyncio.py", line 781, in aexit
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise BaseExceptionGroup(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: +-+---------------- 1 ----------------
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Traceback (most recent call last):
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/uvicorn/protocols/http/httptools_impl.py", line 409, in run_asgi
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | result = await app( # type: ignore[func-returns-value]
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/uvicorn/middleware/proxy_headers.py", line 60, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return await self.app(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/applications.py", line 1133, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await super().call(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/applications.py", line 113, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.middleware_stack(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py", line 186, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py", line 164, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, _send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/sessions.py", line 85, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, send_wrapper)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/cors.py", line 93, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.simple_response(scope, receive, send, request_headers=headers)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/cors.py", line 144, in simple_response
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups():
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in exit
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/main.py", line 1268, in inspect_websocket
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return await call_next(request)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups():
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in exit
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/main.py", line 1247, in check_url
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await call_next(request)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups():
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in exit
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/main.py", line 1233, in commit_session_after_request
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await call_next(request)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups():
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in exit
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/utils/security_headers.py", line 11, in dispatch
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await call_next(request)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups():
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in exit
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/utils.py", line 85, in collapse_excgroups
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/main.py", line 1219, in dispatch
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await call_next(request)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette_compress/__init_.py", line 92, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return await self._zstd(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette_compress/_zstd_legacy.py", line 100, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, wrapper)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/exceptions.py", line 63, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py", line 53, in wrapped_app
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py", line 42, in wrapped_app
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await app(scope, receive, sender)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/middleware/asyncexitstack.py", line 18, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/routing.py", line 716, in call
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.middleware_stack(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/routing.py", line 736, in app
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await route.handle(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/routing.py", line 290, in handle
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/routing.py", line 123, in app
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await wrap_app_handling_exceptions(app, request)(scope, receive, send)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py", line 53, in wrapped_app
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py", line 42, in wrapped_app
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await app(scope, receive, sender)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/routing.py", line 109, in app
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await f(request)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/routing.py", line 387, in app
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raw_response = await run_endpoint_function(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/routing.py", line 288, in run_endpoint_function
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return await dependant.call(**values)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/routers/audio.py", line 526, in speech
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | load_speech_pipeline(request)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/routers/audio.py", line 302, in load_speech_pipeline
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | request.app.state.speech_synthesiser = pipeline(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/__init__.py", line 1027, in pipeline
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | framework, model = infer_framework_load_model(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/base.py", line 333, in infer_framework_load_model
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise ValueError(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ValueError: Could not load model microsoft/speecht5_tts with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForTextToWaveform'>, <class 'transformers.models.auto.modeling_auto.AutoModelForTextToSpectrogram'>, <class 'transformers.models.speecht5.modeling_speecht5.SpeechT5ForTextToSpeech'>). See the original errors:
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: |
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | while loading with AutoModelForTextToWaveform, an error is thrown:
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Traceback (most recent call last):
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/base.py", line 293, in infer_framework_load_model
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | model = model_class.from_pretrained(model, **kwargs)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/models/auto/auto_factory.py", line 607, in from_pretrained
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise ValueError(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ValueError: Unrecognized configuration class <class 'transformers.models.speecht5.configuration_speecht5.SpeechT5Config'> for this kind of AutoModel: AutoModelForTextToWaveform.
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Model type should be one of BarkConfig, CsmConfig, FastSpeech2ConformerConfig, FastSpeech2ConformerWithHifiGanConfig, MusicgenConfig, MusicgenMelodyConfig, Qwen2_5OmniConfig, Qwen3OmniMoeConfig, SeamlessM4TConfig, SeamlessM4Tv2Config, VitsConfig.
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: |
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | During handling of the above exception, another exception occurred:
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: |
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Traceback (most recent call last):
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/base.py", line 311, in infer_framework_load_model
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | model = model_class.from_pretrained(model, **fp32_kwargs)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/models/auto/auto_factory.py", line 607, in from_pretrained
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise ValueError(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ValueError: Unrecognized configuration class <class 'transformers.models.speecht5.configuration_speecht5.SpeechT5Config'> for this kind of AutoModel: AutoModelForTextToWaveform.
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Model type should be one of BarkConfig, CsmConfig, FastSpeech2ConformerConfig, FastSpeech2ConformerWithHifiGanConfig, MusicgenConfig, MusicgenMelodyConfig, Qwen2_5OmniConfig, Qwen3OmniMoeConfig, SeamlessM4TConfig, SeamlessM4Tv2Config, VitsConfig.
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: |
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | while loading with AutoModelForTextToSpectrogram, an error is thrown:
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Traceback (most recent call last):
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/base.py", line 293, in infer_framework_load_model
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | model = model_class.from_pretrained(model, **kwargs)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/models/auto/auto_factory.py", line 604, in from_pretrained
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return model_class.from_pretrained(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/modeling_utils.py", line 277, in _wrapper
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return func(*args, **kwargs)
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/modeling_utils.py", line 5051, in from_pretrained
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ) = cls._load_pretrained_model(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/modeling_utils.py", line 5319, in _load_pretrained_model
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | load_state_dict(checkpoint_files[0], map_location="meta", weights_only=weights_only).keys()
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/modeling_utils.py", line 508, in load_state_dict
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | check_torch_load_is_safe()
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/utils/import_utils.py", line 1647, in check_torch_load_is_safe
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise ValueError(
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ValueError: Due to a serious vulnerability issue in torch.load, even with weights_only=True, we now require users to upgrade torch to at least v2.6 in order to use the function. This version restriction does not apply when loading files with safetensors.
Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | See the vulnerability report here https://nvd.nist.gov/vuln/detail/CVE-2025-32434

Additional Information

No response

Originally created by @MAWK0235 on GitHub (Nov 3, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/18878 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Pip Install ### Open WebUI Version v0.6.34 ### Ollama Version (if applicable) 0.12.3 ### Operating System Ubuntu 24.04.3 LTS ### Browser (if applicable) Firefox ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior click the TTS button and receive a vocal reading of a response ### Actual Behavior Currently, using the "tts-1" text-to-speech engine triggers an infinite loop when a user activates the text-to-speech functionality. This is due to a recent change in PyTorch. PyTorch v2.6 or higher is now required to load the model used by tts-1 due to a security vulnerability. The error message received is: "ValueError: Due to a serious vulnerability issue in `torch.load`, even with `weights_only=True`, we now require users to upgrade torch to at least v2.6 in order to use the function. This version restriction does not apply when loading files with safetensors." **Resolution:** Upgrade the PyTorch installation to version 2.6 or later. Consider migrating the model to a `safetensors` format to avoid this restriction in the future. (See attached logs for details.) ### Steps to Reproduce **Steps to Reproduce: TTS-1 Text-to-Speech Failure** **Step 1: Configure Text-to-Speech to "tts-1"** 1. Navigate to the application's "Text-to-Speech" settings 2. Select "tts-1" as the active text-to-speech engine. 3. Save the changes to the settings. **Step 2: Query the LLM** 1. Using the application's interface, formulate a question or prompt for the integrated Large Language Model. (Example: "Tell me a short story about a cat.") 2. Submit the prompt to the LLM. 3. Wait for the LLM to generate a response. Verify the LLM response is appearing in the application. **Step 3: Monitor Logs (Pre-Failure)** 1. Open the application's log file or logging console. (Specify the location of the log file). 2. Observe the logs for any initial messages related to the LLM response or TTS engine initialization. (This is to confirm the application is starting up normally). You should see logs showing the LLM response being received. **Step 4: Activate Text-to-Speech and Monitor Failure** 1. Locate the "Text-to-Speech" button or control associated with the LLM’s response. 2. Click the "Text-to-Speech" button. 3. **Monitor the application’s behavior and the logs *immediately* after clicking the button.** **Expected Result/Failure:** * The application will likely enter a loop, becoming unresponsive or freezing. * The logs will display the `ValueError` related to the PyTorch version requirement. The error message should be similar to this: ``` ValueError: Due to a serious vulnerability issue in `torch.load`, even with `weights_only=True`, we now require users to upgrade torch to at least v2.6 in order to use the function. This version restriction does not apply when loading files with safetensors. ``` * You may observe repeated error messages in the logs related to loading the PyTorch model. ### Logs & Screenshots <img width="1707" height="100" alt="Image" src="https://github.com/user-attachments/assets/c6970a1a-fe14-463d-8982-1a0abc2f5d37" /> <img width="2412" height="894" alt="Image" src="https://github.com/user-attachments/assets/5e0c8123-6294-4d02-b026-bd4d61cb3d9c" /> <img width="3991" height="984" alt="Image" src="https://github.com/user-attachments/assets/780f0d2f-f50e-4059-a53b-47b06e325887" /> Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: 2025-11-03 02:20:09.194 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 192.168.1.14:0 - "POST /api/v1/audio/speech HTTP/1.1" 500 Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: Exception in ASGI application Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: + Exception Group Traceback (most recent call last): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 79, in collapse_excgroups Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | yield Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 183, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | async with anyio.create_task_group() as task_group: Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/anyio/_backends/_asyncio.py", line 781, in __aexit__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise BaseExceptionGroup( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: +-+---------------- 1 ---------------- Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Traceback (most recent call last): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/uvicorn/protocols/http/httptools_impl.py", line 409, in run_asgi Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | result = await app( # type: ignore[func-returns-value] Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return await self.app(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/applications.py", line 1133, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await super().__call__(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/applications.py", line 113, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.middleware_stack(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py", line 186, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py", line 164, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, _send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/sessions.py", line 85, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, send_wrapper) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/cors.py", line 93, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.simple_response(scope, receive, send, request_headers=headers) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/cors.py", line 144, in simple_response Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups(): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in __exit__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/main.py", line 1268, in inspect_websocket Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return await call_next(request) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups(): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in __exit__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/main.py", line 1247, in check_url Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await call_next(request) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups(): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in __exit__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/main.py", line 1233, in commit_session_after_request Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await call_next(request) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups(): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in __exit__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/utils/security_headers.py", line 11, in dispatch Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await call_next(request) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 182, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | with recv_stream, send_stream, collapse_excgroups(): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/lib/python3.12/contextlib.py", line 158, in __exit__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | self.gen.throw(value) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_utils.py", line 85, in collapse_excgroups Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 184, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await self.dispatch_func(request, call_next) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/main.py", line 1219, in dispatch Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await call_next(request) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 159, in call_next Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise app_exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/base.py", line 144, in coro Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive_or_disconnect, send_no_error) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette_compress/__init__.py", line 92, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return await self._zstd(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette_compress/_zstd_legacy.py", line 100, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, wrapper) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/middleware/exceptions.py", line 63, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py", line 53, in wrapped_app Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py", line 42, in wrapped_app Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await app(scope, receive, sender) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/routing.py", line 716, in __call__ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.middleware_stack(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/routing.py", line 736, in app Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await route.handle(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/routing.py", line 290, in handle Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await self.app(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/routing.py", line 123, in app Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await wrap_app_handling_exceptions(app, request)(scope, receive, send) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py", line 53, in wrapped_app Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise exc Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py", line 42, in wrapped_app Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | await app(scope, receive, sender) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/routing.py", line 109, in app Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | response = await f(request) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/routing.py", line 387, in app Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raw_response = await run_endpoint_function( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/fastapi/routing.py", line 288, in run_endpoint_function Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return await dependant.call(**values) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/routers/audio.py", line 526, in speech Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | load_speech_pipeline(request) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/routers/audio.py", line 302, in load_speech_pipeline Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | request.app.state.speech_synthesiser = pipeline( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/__init__.py", line 1027, in pipeline Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | framework, model = infer_framework_load_model( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/base.py", line 333, in infer_framework_load_model Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise ValueError( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ValueError: Could not load model microsoft/speecht5_tts with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForTextToWaveform'>, <class 'transformers.models.auto.modeling_auto.AutoModelForTextToSpectrogram'>, <class 'transformers.models.speecht5.modeling_speecht5.SpeechT5ForTextToSpeech'>). See the original errors: Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | while loading with AutoModelForTextToWaveform, an error is thrown: Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Traceback (most recent call last): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/base.py", line 293, in infer_framework_load_model Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | model = model_class.from_pretrained(model, **kwargs) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/models/auto/auto_factory.py", line 607, in from_pretrained Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise ValueError( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ValueError: Unrecognized configuration class <class 'transformers.models.speecht5.configuration_speecht5.SpeechT5Config'> for this kind of AutoModel: AutoModelForTextToWaveform. Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Model type should be one of BarkConfig, CsmConfig, FastSpeech2ConformerConfig, FastSpeech2ConformerWithHifiGanConfig, MusicgenConfig, MusicgenMelodyConfig, Qwen2_5OmniConfig, Qwen3OmniMoeConfig, SeamlessM4TConfig, SeamlessM4Tv2Config, VitsConfig. Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | During handling of the above exception, another exception occurred: Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Traceback (most recent call last): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/base.py", line 311, in infer_framework_load_model Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | model = model_class.from_pretrained(model, **fp32_kwargs) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/models/auto/auto_factory.py", line 607, in from_pretrained Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise ValueError( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ValueError: Unrecognized configuration class <class 'transformers.models.speecht5.configuration_speecht5.SpeechT5Config'> for this kind of AutoModel: AutoModelForTextToWaveform. Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Model type should be one of BarkConfig, CsmConfig, FastSpeech2ConformerConfig, FastSpeech2ConformerWithHifiGanConfig, MusicgenConfig, MusicgenMelodyConfig, Qwen2_5OmniConfig, Qwen3OmniMoeConfig, SeamlessM4TConfig, SeamlessM4Tv2Config, VitsConfig. Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | while loading with AutoModelForTextToSpectrogram, an error is thrown: Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | Traceback (most recent call last): Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/pipelines/base.py", line 293, in infer_framework_load_model Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | model = model_class.from_pretrained(model, **kwargs) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/models/auto/auto_factory.py", line 604, in from_pretrained Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return model_class.from_pretrained( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/modeling_utils.py", line 277, in _wrapper Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | return func(*args, **kwargs) Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/modeling_utils.py", line 5051, in from_pretrained Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ) = cls._load_pretrained_model( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/modeling_utils.py", line 5319, in _load_pretrained_model Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | load_state_dict(checkpoint_files[0], map_location="meta", weights_only=weights_only).keys() Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/modeling_utils.py", line 508, in load_state_dict Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | check_torch_load_is_safe() Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | File "/usr/local/lib/python3.12/dist-packages/open_webui/../transformers/utils/import_utils.py", line 1647, in check_torch_load_is_safe Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | raise ValueError( Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | ValueError: Due to a serious vulnerability issue in `torch.load`, even with `weights_only=True`, we now require users to upgrade torch to at least v2.6 in order to use the function. This version restriction does not apply when loading files with safetensors. Nov 03 02:20:09 OpenWebUI start-all.sh[2734]: | See the vulnerability report here https://nvd.nist.gov/vuln/detail/CVE-2025-32434 ### Additional Information _No response_

GiteaMirror added the bug label 2026-04-25 08:08:20 -05:00

GiteaMirror closed this issue 2026-04-25 08:08:22 -05:00

GiteaMirror commented 2026-04-25 08:08:25 -05:00

Author

Owner

Copy Link

Copy Source

@tjbck commented on GitHub (Nov 5, 2025):

Deployment dependent, unable to reproduce.

<!-- gh-comment-id:3493308099 --> @tjbck commented on GitHub (Nov 5, 2025): Deployment dependent, unable to reproduce.

Sign in to join this conversation.

No Branch/Tag Specified

Branches Tags

main

dev

v0.13.3

v0.13.2

v0.13.1

v0.13.0

v0.12.5

v0.12.4

v0.12.3

v0.12.2

v0.12.1

v0.12.0

v0.11.4

v0.11.3

v0.11.2

v0.11.1

v0.11.0

v0.10.2

v0.10.1

v0.10.0

v0.9.6

v0.9.5

v0.9.4

v0.9.3

v0.9.2

v0.9.1

v0.9.0

v0.8.12

v0.8.11

v0.8.10

v0.8.9

v0.8.8

v0.8.7

v0.8.6

v0.8.5

v0.8.4

v0.8.3

v0.8.2

v0.8.1

v0.8.0

v0.7.2

v0.7.1

v0.7.0

v0.6.43

v0.6.42

v0.6.41

v0.6.40

v0.6.39

v0.6.38

v0.6.37

v0.6.36

v0.6.35

v0.6.34

v0.6.33

v0.6.32

v0.6.31

v0.6.30

v0.6.29

v0.6.28

v0.6.27

v0.6.26

v0.6.25

v0.6.24

v0.6.23

v0.6.22

v0.6.21

v0.6.20

v0.6.19

v0.6.18

v0.6.17

v0.6.16

v0.6.15

v0.6.14

v0.6.13

v0.6.12

v0.6.11

v0.6.10

v0.6.9

v0.6.8

v0.6.7

v0.6.6

v0.6.5

v0.6.4

v0.6.3

v0.6.2

v0.6.1

v0.6.0

v0.5.20

v0.5.19

v0.5.18

v0.5.17

v0.5.16

v0.5.15

v0.5.14

v0.5.13

v0.5.12

v0.5.11

v0.5.10

v0.5.9

v0.5.8

v0.5.7

v0.5.6

v0.5.5

v0.5.4

v0.5.3

v0.5.2

v0.5.1

v0.5.0

v0.4.8

v0.4.7

v0.4.6

v0.4.5

v0.4.4

v0.4.3

v0.4.2

v0.4.1

v0.4.0

v0.3.35

v0.3.34

v0.3.33

v0.3.32

v0.3.31

v0.3.30

v0.3.29

v0.3.28

v0.3.27

v0.3.26

v0.3.25

v0.3.24

v0.3.23

v0.3.22

v0.3.21

v0.3.20

v0.3.19

v0.3.18

v0.3.17

v0.3.16

v0.3.15

v0.3.14

v0.3.13

v0.3.12

v0.3.11

v0.3.10

v0.3.9

v0.3.8

v0.3.7

v0.3.6

v0.3.5

v0.3.4

v0.3.3

v0.3.2

v0.3.1

v0.3.0

v0.2.5

v0.2.4

v0.2.3

v0.2.2

v0.2.1

v0.2.0

v0.1.125

v0.1.124

v0.1.123

v0.1.122

v0.1.121

v0.1.120

v0.1.119

v0.1.118

v0.1.117

v0.1.116

v0.1.115

v0.1.114

v0.1.113

v0.1.112

v0.1.111

v0.1.110

v0.1.109

v0.1.108

v0.1.107

v0.1.106

v0.1.105

v0.1.104

v0.1.103

v0.1.102

Labels

Clear labels

bug

confirmed

confirmed issue

core

documentation

enhancement

good first issue

help wanted

non-core

pull-request

Mirrored from GitHub Pull Request

python

question

testing wanted

No labels bug

Milestone

No items

No Milestone

Projects

Clear projects

No projects

Assignees

Clear assignees

GiteaMirror ninjasurge (Kaehlen Rog)

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#34231