mirror of
https://github.com/chidiwilliams/buzz.git
synced 2026-03-23 02:24:38 +01:00
120 lines
No EOL
6.3 KiB
XML
120 lines
No EOL
6.3 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<component type="desktop-application">
|
|
<id>io.github.chidiwilliams.Buzz</id>
|
|
|
|
<name>Buzz</name>
|
|
<summary>Transcribe and translate audio</summary>
|
|
<metadata_license>CC0-1.0</metadata_license>
|
|
<project_license>MIT</project_license>
|
|
<developer_name>Chidi Williams</developer_name>
|
|
|
|
<description>
|
|
<p>
|
|
Buzz transcribes and translates audio to text offline using OpenAI's Whisper. Import audio and video files into Buzz and export them as TXT, SRT, or VTT files. Buzz supports Whisper, Whisper.cpp, Faster Whisper, Whisper-compatible models from the Hugging Face repository, and the OpenAI Whisper API.
|
|
</p>
|
|
<p>
|
|
Required permissions in Buzz will let you select audio and video files for transcription, from most common file location on your computer. Network permission is used to download transcription model files. Microphone permission lets you transcribe real time speech.
|
|
</p>
|
|
<p>
|
|
Note: If your system theme is not applied to Buzz, ensure it is in <code>~/.themes</code> folder. You may need to copy the system themes to this folder <code>cp -r /usr/share/themes/ ~/.themes/</code> and give Flatpaks access to this folder <code>flatpak override --user --filesystem=~/.themes</code>.
|
|
</p>
|
|
</description>
|
|
|
|
<categories>
|
|
<category>AudioVideo</category>
|
|
</categories>
|
|
|
|
<url type="bugtracker">https://github.com/chidiwilliams/buzz/issues</url>
|
|
<url type="homepage">https://github.com/chidiwilliams/buzz</url>
|
|
<url type="faq">https://chidiwilliams.github.io/buzz/docs</url>
|
|
|
|
<branding>
|
|
<color type="primary" scheme_preference="light">#f66151</color>
|
|
<color type="primary" scheme_preference="dark">#45124d</color>
|
|
</branding>
|
|
|
|
<requires>
|
|
<control>keyboard</control>
|
|
<control>pointing</control>
|
|
</requires>
|
|
<launchable type="desktop-id">io.github.chidiwilliams.Buzz.desktop</launchable>
|
|
<screenshots>
|
|
<screenshot type="default">
|
|
<image>https://raw.githubusercontent.com/chidiwilliams/buzz/98ea5b2f1b209e26d8ac49313e23697b88dce01d/share/screenshots/buzz-1-import.png</image>
|
|
<caption>File and url import options</caption>
|
|
</screenshot>
|
|
<screenshot>
|
|
<image>https://raw.githubusercontent.com/chidiwilliams/buzz/98ea5b2f1b209e26d8ac49313e23697b88dce01d/share/screenshots/buzz-2-main_screen.png</image>
|
|
<caption>Main screen with transcription results</caption>
|
|
</screenshot>
|
|
<screenshot>
|
|
<image>https://raw.githubusercontent.com/chidiwilliams/buzz/98ea5b2f1b209e26d8ac49313e23697b88dce01d/share/screenshots/buzz-3-preferences.png</image>
|
|
<caption>Application preferences</caption>
|
|
</screenshot>
|
|
<screenshot>
|
|
<image>https://raw.githubusercontent.com/chidiwilliams/buzz/98ea5b2f1b209e26d8ac49313e23697b88dce01d/share/screenshots/buzz-4-transcript.png</image>
|
|
<caption>Transcript with options for further processing and export</caption>
|
|
</screenshot>
|
|
<screenshot>
|
|
<image>https://raw.githubusercontent.com/chidiwilliams/buzz/98ea5b2f1b209e26d8ac49313e23697b88dce01d/share/screenshots/buzz-5-live_recording.png</image>
|
|
<caption>Live recording transcription and translation options</caption>
|
|
</screenshot>
|
|
</screenshots>
|
|
|
|
<content_rating type="oars-1.1"/>
|
|
|
|
<releases>
|
|
<release version="1.4.0" date="2025-12-20">
|
|
<url type="details">https://github.com/chidiwilliams/buzz/releases/tag/v1.4.0</url>
|
|
<description>
|
|
<p>Adding speaker identification on transcriptions and video support for transcription viewer, improvements to transcription table and support for over 1000 of worlds languages via MMS models.</p>
|
|
<p>Release details:</p>
|
|
<ul>
|
|
<li>Speaker identification on finished transcripts</li>
|
|
<li>Support for video in transcription viewer</li>
|
|
<li>Ability to add notes and restart transcriptions in main table</li>
|
|
<li>Adding support for more than 1000 languages via MMS model family when transcribing with Huggingface transcription type</li>
|
|
<li>Adding support for PEFT models when transcribing with Huggingface transcription type</li>
|
|
<li>Adding support for 8bit quantization for Huggingface and faster Whisper transcriptions</li>
|
|
<li>Updated libraries and dependencies to support latest GPUs</li>
|
|
<li>Support for secrets portal for snap packages on Linux</li>
|
|
<li>Ability to specify model to use when transcribing with OpenAI API</li>
|
|
<li>Ability to access application logs from About screen</li>
|
|
</ul>
|
|
</description>
|
|
</release>
|
|
<release version="1.3.3" date="2025-11-09">
|
|
<url type="details">https://github.com/chidiwilliams/buzz/releases/tag/v1.3.3</url>
|
|
<description>
|
|
<p>This release introduces Vulkan GPU support for whisper.cpp making it significantly faster even on laptops.
|
|
Real-time transcription is possible even with large models on computers with ~5GB RAM video cards. There
|
|
is now an option to separate voice tracks before the audio is transcribed. This can improve transcript
|
|
accuracy for audios with background noises or music. Faster whisper was updated to the latest version
|
|
adding noticeable speed improvement.</p>
|
|
<p>Additional improvements:</p>
|
|
<ul>
|
|
<li>Option to switch the UI language from preferences</li>
|
|
<li>Library updates for better Linux compatibility, especially in Flatpak installations</li>
|
|
<li>Option to upload live transcripts to a server</li>
|
|
<li>Search and additional controls in Transcription viewer</li>
|
|
<li>Added UI translation for German, Dutch, Danish and Portuguese (Brazilian)</li>
|
|
<li>Minor bug fixes</li>
|
|
</ul>
|
|
</description>
|
|
</release>
|
|
<release version="1.2.0" date="2024-11-24">
|
|
<url type="details">https://github.com/chidiwilliams/buzz/releases/tag/v1.2.0</url>
|
|
<description>
|
|
<p>Added support for Dark mode and the Turbo models. More details:</p>
|
|
<ul>
|
|
<li>Dark mode support</li>
|
|
<li>Improved support for GPUs and Apple Core ML</li>
|
|
<li>Added support for the Turbo models</li>
|
|
<li>Sliding window mode for live transcriptions</li>
|
|
<li>Bugfixes and other small improvements</li>
|
|
<li>Japanese UI translations</li>
|
|
</ul>
|
|
</description>
|
|
</release>
|
|
</releases>
|
|
</component> |