# QwenLM/Qwen-Audio

The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.

Repository: https://github.com/QwenLM/Qwen-Audio
Canonical: https://ross.abutalabs.com/products/qwen-audio
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-07-05T09:17:49+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 73
- inputs: {"age_days": 1030, "days_push": 789, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1945, forks 147 (observed 2026-08-28T04:05:57.716033+00:00)

## What it is
Official repository for Qwen-Audio, Alibaba Cloud's large audio-language model with pretrained and chat variants. It provides model weights, inference code, and evaluation for understanding speech, music, and environmental sounds.

## Use cases
- transcribe speech to text with a large audio model
- build a chatbot that understands audio input
- classify acoustic scenes and sound events
- analyze music or vocals with an LLM
- run audio question answering on GPU

## When to avoid
- you only need lightweight ASR with low latency
- you require a permissive license - the license is custom (NOASSERTION)
- you need a maintained project with frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: speech-recognition, audio-processing, llm-inference, chatbot, machine-learning
- domain: speech-processing, large-language-models, artificial-intelligence
- platform: python
- tags: audio-language-model, multimodal, qwen, alibaba-cloud, pretrained-model, audio-understanding, audio, natural-language-processing, gpu, linux

## Member repositories
- QwenLM/Qwen-Audio (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:57.716033+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:07:21.678866+00:00, confidence not recorded.
  - readme: https://github.com/QwenLM/Qwen-Audio (fetched 2026-08-28T04:05:57.716033+00:00, sha 8087851c35de)
- Data as of 2026-08-30T08:39:29.467469+00:00.