langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-20 19:50:06 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

stt chat process fail #13816

New Issue
Closed
opened 2026-02-21 19:14:00 -05:00 by yindo · 2 comments
yindo commented 2026-02-21 19:14:00 -05:00
Owner
Copy Link
Copy Source

Originally created by @zhangshuoa on GitHub (May 13, 2025).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)
  • Please do not modify this template :) and fill in all the required fields.

Dify version

Version 1.2.0

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

I have deployed a model locally and integrated it into a chat flow using a Speech To Text plugin. However, after uploading an audio file, I could see that it started processing, but after more than 20 minutes, the process was terminated without any output. Surprisingly, the log shows the status as "success."

This conflicting information has left me unsure of how to proceed with troubleshooting. The audio file I uploaded is 26MB in size and 29 minutes long. I’ve already adjusted the file size upload limit, so now I’m not sure what’s going wrong or where the issue is occurring.

model name: speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch
model deploy: gpustack

Image Image

✔️ Expected Behavior

There is a clear return message.

❌ Actual Behavior

No responses.

Image
Originally created by @zhangshuoa on GitHub (May 13, 2025). ### Self Checks - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [x] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:) - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version Version 1.2.0 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce I have deployed a model locally and integrated it into a chat flow using a Speech To Text plugin. However, after uploading an audio file, I could see that it started processing, but after more than 20 minutes, the process was terminated without any output. Surprisingly, the log shows the status as "success." This conflicting information has left me unsure of how to proceed with troubleshooting. The audio file I uploaded is 26MB in size and 29 minutes long. I’ve already adjusted the file size upload limit, so now I’m not sure what’s going wrong or where the issue is occurring. model name: speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch model deploy: gpustack <img width="575" alt="Image" src="https://github.com/user-attachments/assets/68cad103-3d20-4664-80c5-fcce71993349" /> <img width="524" alt="Image" src="https://github.com/user-attachments/assets/1bad2b33-9e07-44f4-a118-9723c5758875" /> ### ✔️ Expected Behavior There is a clear return message. ### ❌ Actual Behavior No responses. <img width="912" alt="Image" src="https://github.com/user-attachments/assets/e13a61dd-dae6-4ad5-af04-00244e265b11" />
yindo added the stt & tts label 2026-02-21 19:14:00 -05:00
yindo closed this issue 2026-02-21 19:14:00 -05:00
yindo commented 2026-02-21 19:14:00 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (May 13, 2025):

Hello @zhangshuoa! 👋 I'm Dosu, your friendly bot here to help you tackle bugs, answer questions, and guide you on your journey to becoming a contributor. I'm ready to assist you while we wait for a human maintainer. Let's get started! 🚀

I found a similar closed issue that might be relevant to your problem. The issue titled Speech to text error was resolved by a pull request that fixed incorrect ASR parameters [1].

For your specific case, here are some troubleshooting steps you can consider:

  1. Check Logging Mechanisms: Dify uses logging.exception() in the TextApi class to capture detailed error information. Look for logs with messages like "App model config broken." or "internal server error" to diagnose the issue [2].

  2. Verify Model Configuration: Ensure that the model speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch is correctly configured and deployed. Double-check the deployment settings on gpustack.

  3. Review Audio File Specifications: Although you've adjusted the file size limit, ensure that the audio file format is supported (e.g., flac, mp3, mp4, etc.) and that there are no issues with the audio content itself.

  4. Resource Allocation: Consider checking if there are any resource allocation issues, such as insufficient memory or CPU resources, that might be causing the process to terminate unexpectedly.

  5. Timeout Settings: Investigate if there are any timeout settings that might be affecting the processing of longer audio files.

These steps should help you identify the root cause of the issue. If the problem persists, reviewing the detailed logs and configuration settings might provide further insights.

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other

@dosubot[bot] commented on GitHub (May 13, 2025): <!-- Greeting --> Hello @zhangshuoa! 👋 I'm [Dosu](https://dosu.dev), your friendly bot here to help you tackle bugs, answer questions, and guide you on your journey to becoming a contributor. I'm ready to assist you while we wait for a human maintainer. Let's get started! 🚀 <!-- Answer --> I found a similar closed issue that might be relevant to your problem. The issue titled [Speech to text error](https://github.com/langgenius/dify/issues/2158) was resolved by a pull request that fixed incorrect ASR parameters <sup>[[1]](https://github.com/langgenius/dify/issues/2158)</sup>. For your specific case, here are some troubleshooting steps you can consider: 1. **Check Logging Mechanisms**: Dify uses `logging.exception()` in the `TextApi` class to capture detailed error information. Look for logs with messages like "App model config broken." or "internal server error" to diagnose the issue <sup>[[2]](https://github.com/langgenius/dify/blob/main/api/controllers/service_api/app/audio.py)</sup>. 2. **Verify Model Configuration**: Ensure that the model `speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch` is correctly configured and deployed. Double-check the deployment settings on `gpustack`. 3. **Review Audio File Specifications**: Although you've adjusted the file size limit, ensure that the audio file format is supported (e.g., flac, mp3, mp4, etc.) and that there are no issues with the audio content itself. 4. **Resource Allocation**: Consider checking if there are any resource allocation issues, such as insufficient memory or CPU resources, that might be causing the process to terminate unexpectedly. 5. **Timeout Settings**: Investigate if there are any timeout settings that might be affecting the processing of longer audio files. These steps should help you identify the root cause of the issue. If the problem persists, reviewing the detailed logs and configuration settings might provide further insights. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/f69941fa-0b3d-4697-8ea2-831cb33df8cd?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/f69941fa-0b3d-4697-8ea2-831cb33df8cd?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/f69941fa-0b3d-4697-8ea2-831cb33df8cd?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/f69941fa-0b3d-4697-8ea2-831cb33df8cd?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/f69941fa-0b3d-4697-8ea2-831cb33df8cd?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/f69941fa-0b3d-4697-8ea2-831cb33df8cd?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/f69941fa-0b3d-4697-8ea2-831cb33df8cd?feedback_type=other)</sup>
yindo commented 2026-02-21 19:14:00 -05:00
Author
Owner
Copy Link
Copy Source

@zhangshuoa commented on GitHub (May 13, 2025):

I wonder if there is a time limit for workflows or chat flows，what name is it.

@zhangshuoa commented on GitHub (May 13, 2025): I wonder if there is a time limit for workflows or chat flows，what name is it.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label stt & tts
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#13816
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?