Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error 500 and Timeout Issues When Transcribing Audio Files Using Wit.AI API #2765

Open
MesterPerfect opened this issue Nov 16, 2024 · 0 comments

Comments

@MesterPerfect
Copy link

Do you want to request a feature, report a bug, or ask a question about wit?

I would like to report a bug.

What is the current behavior?

When attempting to use Wit.AI for transcribing audio files via the API, the process initiates correctly, splitting the file into multiple clips. However, during the transcription phase, the API encounters errors, including 500 Internal Server Errors and 408 Timeout Errors.

The following logs illustrate the issue:

(2024-11-16 14:23:45,297) | root | INFO => 'started transcriber using Wit.AI.'
(2024-11-16 14:23:45,320) | root | INFO => 'Splitting the file'
(2024-11-16 14:23:45,323) | root | INFO => 'The clip will be split into mp3 files.'
(2024-11-16 14:23:47,121) | root | INFO => 'The splitting the file has finished.'
(2024-11-16 14:23:47,121) | root | INFO => 'The file is split into 9 clips.'
(2024-11-16 14:23:47,135) | root | INFO => 'Extracting the text.'
(2024-11-16 14:23:47,135) | root | INFO => 'send 2 requests simultaneously.'
(2024-11-16 14:23:56,730) | root | ERROR => '500 wit'
(2024-11-16 14:23:58,084) | root | ERROR => '408 timeout'
(2024-11-16 14:24:02,576) | root | ERROR => '500 wit'
(2024-11-16 14:24:38,776) | root | ERROR => '200 wit'
(2024-11-16 14:24:49,000) | root | ERROR => '408 timeout'
(2024-11-16 14:24:49,001) | root | ERROR => 'An error occurred while extracting the text.'
(2024-11-16 14:24:49,006) | root | INFO => 'Paused transcriber.'

If the current behavior is a bug, please provide the steps to reproduce and if possible a minimal demo of the problem.

  1. Use Wit.AI’s API to transcribe an audio file.
  2. Begin the transcription process, which includes splitting the audio file into smaller clips.
  3. During the transcription phase, API requests frequently encounter 500 errors and timeout errors (408).
  4. As a result, transcription fails, and an error message is logged.

What is the expected behavior?

The API should successfully process each clip, returning the transcribed text without encountering server errors or timeouts.

If applicable, what is the App ID where you are experiencing this issue? If you do not provide this, we cannot help.

App ID: [2136034510061171]

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant