QwenLM/Qwen2-Audio

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2099 stars · 169 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official repository for Qwen2-Audio, a 7B-parameter large audio-language model from Alibaba Cloud that accepts audio inputs and responds to speech or text instructions. It provides model weights, inference code, and evaluation for voice chat and audio analysis tasks.

Use cases

• transcribe speech to text with a large audio model
• build a voice chat assistant that takes audio input
• analyze audio clips with text instructions
• recognize speech emotion from audio
• translate speech to text across languages
• classify vocal sounds in recordings

When to choose

• you need a single model handling ASR, speech translation, and audio understanding
• you want voice-only interaction without text input
• you need an open 7B audio-language model to fine-tune or self-host

When to avoid

• you need lightweight or on-device speech recognition
• you only need a dedicated ASR engine like Whisper
• you require a permissive license - the repo lists no license

Facets

library · maturity active

speech-recognition audio-processing llm-inference machine-learning speech-processing large-language-models artificial-intelligence python audio-language-model multimodal voice-chat qwen transformers model-weights audio gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="QwenLM/Qwen2-Audio")