I propose integrating https://github.com/xenova/whisper-web, a powerful open-source library for speech recognition in the browser, as an alternative to sending audio data to the server for transcription.
Whisper-Web enables real-time, on-device transcription, potentially reducing server load and improving user experience through faster response times and reduced latency. Additionally, this approach enhances user privacy by processing audio locally within the browser.
I envision implementing Whisper-Web as an optional feature alongside the existing server-based transcription, allowing users to choose their preferred method based on their needs.
Whisper-web is under permissive MIT License.
Thank you.
Originally created by @gloryknight on GitHub (Dec 27, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8143
# Feature Request
I propose integrating https://github.com/xenova/whisper-web, a powerful open-source library for speech recognition in the browser, as an alternative to sending audio data to the server for transcription.
Whisper-Web enables real-time, on-device transcription, potentially reducing server load and improving user experience through faster response times and reduced latency. Additionally, this approach enhances user privacy by processing audio locally within the browser.
I envision implementing Whisper-Web as an optional feature alongside the existing server-based transcription, allowing users to choose their preferred method based on their needs.
Whisper-web is under permissive MIT License.
Thank you.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @gloryknight on GitHub (Dec 27, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8143
Feature Request
I propose integrating https://github.com/xenova/whisper-web, a powerful open-source library for speech recognition in the browser, as an alternative to sending audio data to the server for transcription.
Whisper-Web enables real-time, on-device transcription, potentially reducing server load and improving user experience through faster response times and reduced latency. Additionally, this approach enhances user privacy by processing audio locally within the browser.
I envision implementing Whisper-Web as an optional feature alongside the existing server-based transcription, allowing users to choose their preferred method based on their needs.
Whisper-web is under permissive MIT License.
Thank you.