metadata

title: Qwen2 Audio Demo
emoji: 🎵
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.7.1
app_file: app.py
pinned: false

Qwen2 Audio Demo

This is a Hugging Face Space demo for the Qwen2-Audio-7B model. The app allows users to upload audio files and get AI-generated descriptions or answers to specific questions about the audio content.

Features

Upload audio files (supports WAV, MP3, OGG, and FLAC formats)
Ask specific questions about the audio content
Get AI-generated descriptions of the audio
Real-time streaming responses

Usage

Upload an audio file using the audio input interface
(Optional) Enter a specific question about the audio content
Click "Submit" to get the AI's response
The model will process the audio and generate a response in real-time

Model

This demo uses the NexaAIDev/Qwen2-Audio-7B-GGUF model, which is optimized for audio understanding and processing.

Requirements

See requirements.txt for a full list of dependencies.