[PR #13376] [MERGED] feat: Added WHISPER_LANGUAGE env variable #23172

Closed
opened 2026-04-20 04:40:49 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/13376
Author: @Thaniel94
Created: 4/30/2025
Status: Merged
Merged: 5/2/2025
Merged by: @tjbck

Base: devHead: add-whisper-language-constraint


📝 Commits (3)

  • 1efa708 Added WHISPER_LANGUAGE env variable. If set to a country's ISO2, constrains Whisper's stt to that language. Detects language as normal if unset
  • ef7acfb WHISPER_LANGUAGE no longer a "PersistentConfig" variable (Was not appropriate with how WHISPER_LANGUAGE is currently configured).
  • cc14aac Improvements to parsing of WHISPER_LANGUAGE environment variable (Setting as empty string now equivalent to unsetting/removing WHISPER_LANGUAGE). Resolved crash caused when unset

📊 Changes

3 files changed (+4 additions, -0 deletions)

View changed files

📝 backend/open_webui/config.py (+1 -0)
📝 backend/open_webui/main.py (+1 -0)
📝 backend/open_webui/routers/audio.py (+2 -0)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions and describe your changes before submitting a pull request.

See discussion post:
https://github.com/open-webui/open-webui/discussions/13240

Before submitting, make sure you've checked the following:

  • Target branch: Please verify that the pull request targets the dev branch.

  • Description: Provide a concise description of the changes made in this pull request.

  • Adds a new environment variable - 'WHISPER_LANGUAGE'. When set correctly, forces whisper stt to use the set language.
    When unset, or set to an empty string, predicts the language as it did previously.

  • Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.

  • Documentation: Have you updated relevant documentation Open WebUI Docs, or other documentation sources?

  • Should this be accepted, documentation change ready to be added in another pull request - https://github.com/Thaniel94/docs/tree/add-whisper-language-constraint.

  • Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?

  • Testing: Have you written and run sufficient tests to validate the changes?

  • Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?

  • Prefix: To clearly categorize this pull request, prefix the pull request title using one of the following:

    • BREAKING CHANGE: Significant changes that may affect compatibility
    • build: Changes that affect the build system or external dependencies
    • ci: Changes to our continuous integration processes or workflows
    • chore: Refactor, cleanup, or other non-functional code changes
    • docs: Documentation update or addition
    • feat: Introduces a new feature or enhancement to the codebase
    • fix: Bug fix or error correction
    • i18n: Internationalization or localization changes
    • perf: Performance improvement
    • refactor: Code restructuring for better maintainability, readability, or scalability
    • style: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.)
    • test: Adding missing tests or correcting existing tests
    • WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Description

  • Whisper is not always reliable with language detection, but it does offer a way of forcing a specific language, through the 'language' argument in the Whisper transcribe call.
  • Previously Openwebui did not appear to make use of this functionality, so the 'WHISPER_LANGUAGE' environment variable has been added to optionally fill this argument, giving the user the ability to force the STT language, if they prefer.
  • I think this would be helpful for anyone that is having trouble with Whisper's STT language detection (either due to a bad microphone, it not being their first language, or other), and wants to lock it down through an environment variable.
  • A simple low risk change, that adds a bit of extra flexibility for Whisper

Added

  • WHISPER_LANGUAGE environment variable (Is not persistent config)

Changed

  • Whisper transcribe call now sets 'WHISPER_LANGUAGE' as the 'language' argument (where before this argument was left unset).

Deprecated

  • [List any deprecated functionality or features that have been removed]

Removed

  • [List any removed features, files, or functionalities]

Fixed

  • [List any fixes, corrections, or bug fixes]

Security

  • [List any new or updated security-related changes, including vulnerability fixes]

Breaking Changes

  • BREAKING CHANGE: [List any breaking changes affecting compatibility or functionality]

Additional Information

  • [Insert any additional context, notes, or explanations for the changes]
    • [Reference any related issues, commits, or other relevant information]

Screenshots or Videos

  • Below: Backend's current response when a bad value for WHISPER_LANGUAGE is set (received when the audio is sent after recording):
    -438425739-b8d6711e-e8b9-46f4-ba6f-5030383052f4

Documentation additions for WHISPER_LANGUAGE (Assuming the change to the logic is acceptable in this pull request, I assume I would be adding another pull request for these doc changes, also considering whether a 'possible values' field should be added. Also appreciate the description in the second screenshot should specifically mention it sets the language for 'Local Whisper')
image
image

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the CONTRIBUTOR_LICENSE_AGREEMENT, and I am providing my contributions under its terms.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/13376 **Author:** [@Thaniel94](https://github.com/Thaniel94) **Created:** 4/30/2025 **Status:** ✅ Merged **Merged:** 5/2/2025 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `dev` ← **Head:** `add-whisper-language-constraint` --- ### 📝 Commits (3) - [`1efa708`](https://github.com/open-webui/open-webui/commit/1efa708f8325e77165f403c0a60e717752c5d7d5) Added WHISPER_LANGUAGE env variable. If set to a country's ISO2, constrains Whisper's stt to that language. Detects language as normal if unset - [`ef7acfb`](https://github.com/open-webui/open-webui/commit/ef7acfbf3d78447b89cc0a4336286835367fb5b0) WHISPER_LANGUAGE no longer a "PersistentConfig" variable (Was not appropriate with how WHISPER_LANGUAGE is currently configured). - [`cc14aac`](https://github.com/open-webui/open-webui/commit/cc14aacaaa6248426aa4bd1c3b2ee984b4ba850b) Improvements to parsing of WHISPER_LANGUAGE environment variable (Setting as empty string now equivalent to unsetting/removing WHISPER_LANGUAGE). Resolved crash caused when unset ### 📊 Changes **3 files changed** (+4 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/config.py` (+1 -0) 📝 `backend/open_webui/main.py` (+1 -0) 📝 `backend/open_webui/routers/audio.py` (+2 -0) </details> ### 📄 Description # Pull Request Checklist ### Note to first-time contributors: Please open a discussion post in [Discussions](https://github.com/open-webui/open-webui/discussions) and describe your changes before submitting a pull request. See discussion post: https://github.com/open-webui/open-webui/discussions/13240 **Before submitting, make sure you've checked the following:** - [x] **Target branch:** Please verify that the pull request targets the `dev` branch. - [x] **Description:** Provide a concise description of the changes made in this pull request. - Adds a new environment variable - 'WHISPER_LANGUAGE'. When set correctly, forces whisper stt to use the set language. When unset, or set to an empty string, predicts the language as it did previously. - [x] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description. - [x] **Documentation:** Have you updated relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs), or other documentation sources? - Should this be accepted, documentation change ready to be added in another pull request - https://github.com/Thaniel94/docs/tree/add-whisper-language-constraint. - [x] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation? - [x] **Testing:** Have you written and run sufficient tests to validate the changes? - [x] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards? - [x] **Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following: - **BREAKING CHANGE**: Significant changes that may affect compatibility - **build**: Changes that affect the build system or external dependencies - **ci**: Changes to our continuous integration processes or workflows - **chore**: Refactor, cleanup, or other non-functional code changes - **docs**: Documentation update or addition - **feat**: Introduces a new feature or enhancement to the codebase - **fix**: Bug fix or error correction - **i18n**: Internationalization or localization changes - **perf**: Performance improvement - **refactor**: Code restructuring for better maintainability, readability, or scalability - **style**: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.) - **test**: Adding missing tests or correcting existing tests - **WIP**: Work in progress, a temporary label for incomplete or ongoing work # Changelog Entry ### Description - Whisper is not always reliable with language detection, but it does offer a way of forcing a specific language, through the 'language' argument in the Whisper transcribe call. - Previously Openwebui did not appear to make use of this functionality, so the 'WHISPER_LANGUAGE' environment variable has been added to optionally fill this argument, giving the user the ability to force the STT language, if they prefer. - I think this would be helpful for anyone that is having trouble with Whisper's STT language detection (either due to a bad microphone, it not being their first language, or other), and wants to lock it down through an environment variable. - A simple low risk change, that adds a bit of extra flexibility for Whisper ### Added - WHISPER_LANGUAGE environment variable (Is not persistent config) ### Changed - Whisper transcribe call now sets 'WHISPER_LANGUAGE' as the 'language' argument (where before this argument was left unset). ### Deprecated - [List any deprecated functionality or features that have been removed] ### Removed - [List any removed features, files, or functionalities] ### Fixed - [List any fixes, corrections, or bug fixes] ### Security - [List any new or updated security-related changes, including vulnerability fixes] ### Breaking Changes - **BREAKING CHANGE**: [List any breaking changes affecting compatibility or functionality] --- ### Additional Information - [Insert any additional context, notes, or explanations for the changes] - [Reference any related issues, commits, or other relevant information] ### Screenshots or Videos - Below: Backend's current response when a bad value for WHISPER_LANGUAGE is set (received when the audio is sent after recording): -![438425739-b8d6711e-e8b9-46f4-ba6f-5030383052f4](https://github.com/user-attachments/assets/3f5cdf2e-ba32-49b8-ba57-58759c4dff4b) Documentation additions for WHISPER_LANGUAGE (Assuming the change to the logic is acceptable in this pull request, I assume I would be adding another pull request for these doc changes, also considering whether a 'possible values' field should be added. Also appreciate the description in the second screenshot should specifically mention it sets the language for 'Local Whisper') ![image](https://github.com/user-attachments/assets/e5341c3e-c805-44a0-8218-9ce65b725999) ![image](https://github.com/user-attachments/assets/6aac9c28-1194-464f-93af-5eb9623d44ae) ### Contributor License Agreement By submitting this pull request, I confirm that I have read and fully agree to the [CONTRIBUTOR_LICENSE_AGREEMENT](CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-20 04:40:49 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#23172