AudioNotes is an audio-video content-to-structured note system built based on FunASR and Qwen2. Its main function is to quickly extract audio and video content, organize it by calling a large model, and convert these content into structured Markdown notes, which is convenient for users to quickly read and understand.
The main functions of AudioNotes include:
Audio and video content identification and extraction:
Use FunASR automatic speech recognition technology to accurately extract text content from audio and video.
Support the processing of multiple audio and video formats to ensure wide applicability.
Structured note generation:
Organize the extracted text content through the Qwen2 model.
Automatically generate structured Markdown notes for users to quickly read and understand.
The content of the notes is clearly organized and contains key information and key points, reducing the time for users to manually organize them.
Conversation with audio and video content:
Provides the ability to engage in interactive dialogue with audio and video content.
Users can ask questions about audio and video content, and the system will answer based on the recognized and organized text content, providing the ability to obtain in-depth information.
If you want to learn more, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
GitHub：https://github.com/harry0703/AudioNotes
Oil tubing:
