An independent research reproduction of the Qwen-Music method for text-to-music generation
GitHub · Dataset · Demo · Reference Paper
Open-Qwen-Music is an independent research reproduction based on the architecture and training methods described in the Qwen-Music Technical Report. It is not an official Qwen release and is not affiliated with, endorsed by, or maintained by the Qwen team or Alibaba Cloud.
The checkpoints in this repository were prepared by this project. They are not official Qwen-Music checkpoints or evaluation artifacts.
Open-Qwen-Music generates 48 kHz stereo music from text descriptions, musical tags, lyrics, and section-level structure. A music language model first produces 25 Hz semantic tokens, which are converted to audio by an acoustic renderer, spectrogram VAE, and bandwidth refiner.
| Component | Provenance |
|---|---|
| Music language model | Initialized from Qwen/Qwen2.5-Omni-3B and further trained by this project |
| Semantic tokenizer | Trained by this project following the semantic-token design described in the reference paper |
| Acoustic renderer | Trained by this project using an implementation informed by the published method and Stable Audio 3 architecture |
| Acoustic VAE | Trained by this project using the architecture documented in the source repository |
| Bandwidth refiner | Trained by this project using the implementation documented in the source repository |
The bundle contains no official Qwen-Music checkpoint. The renderer also uses
the pinned Qwen/Qwen3-Embedding-0.6B text encoder at runtime; that external
model is downloaded separately and is not included in this repository.
| Component | Purpose |
|---|---|
| Music language model | Generates semantic music tokens from the prompt |
| Semantic tokenizer | Converts reference audio into the semantic token space |
| Acoustic renderer | Generates acoustic latents from semantic tokens and text |
| Acoustic VAE | Decodes acoustic latents into a complex spectrogram |
| Bandwidth refiner | Restores high-frequency detail before waveform synthesis |
The semantic interface uses one 32,768-entry codebook at 25 Hz. The released language model uses a plain semantic-token sequence and was trained for 10,000 optimizer updates in two 5,000-update phases.
Clone the project source and install the inference dependencies:
git clone https://github.com/biang15343100-source/Open-Qwen-Music.git
cd Open-Qwen-Music
python -m venv .venv
source .venv/bin/activate
pip install -e ".[render]"
Run the complete text-to-music pipeline with the included prompt:
python scripts/infer.py \
--model oqmtest1451/open-qwen-music-weights \
--prompts examples/prompts.jsonl \
--output-dir outputs/demo \
--device cuda
The default language-model sampling temperature is 0.7. Each prompt produces
a 48 kHz stereo WAV file and a JSON metadata sidecar. See the
GitHub inference guide
for the prompt schema, offline download instructions, and runtime options.
To download the bundle in advance:
hf download oqmtest1451/open-qwen-music-weights \
--local-dir checkpoints/open-qwen-music
python scripts/infer.py \
--model checkpoints/open-qwen-music \
--prompts examples/prompts.jsonl \
--output-dir outputs/demo \
--device cuda
This implementation is inspired by the architecture and training methodology described in the Qwen-Music Technical Report by Xu et al. The paper is cited as the source of the method. Its reported experiments and results belong to the original authors and should not be interpreted as results of this reproduction.
This project uses independently prepared data, training infrastructure, checkpoints, and demonstrations. Differences in data, scale, optimization, and implementation may produce results that differ from the original report.
The training corpus is published as
david-miller-45678/open-qwen-music-dataset-c-minimax-music3.
The model bundle is tied to dataset revision
454294f27d920bb3c1430566bb7f5c153ece4c27, containing 62,417 audio records
and structured annotations in WebDataset format.
The dataset is restricted to non-commercial academic research and includes
source-specific terms. Review its LICENSE, NOTICE, source policy, and
per-record rights metadata before use.
End-to-end inference loads the language model, acoustic renderer, VAE, refiner, and text encoder. A CUDA GPU with bfloat16 support is recommended. CPU execution is intended for interface checks and is not practical for text-to-music generation.
language-model/ Music language model and text tokenizer
semantic-tokenizer/ Audio-to-semantic tokenizer
acoustic-renderer/ Acoustic diffusion transformer
acoustic-vae/ Spectrogram autoencoder
bandwidth-refiner/ High-frequency refinement model
assets/ Latent statistics and semantic embeddings
This is a research reproduction, and it should not be expected to match the original Qwen-Music system. Generated music can contain structural drift, imperfect lyric intelligibility, unstable long-range repetition, and audio artifacts. Outputs may reflect biases in the training data. Review generated audio before publication or downstream use.
This repository contains components with different provenance.
The language-model component is derived from Qwen/Qwen2.5-Omni-3B and remains
subject to the included Qwen Research License. The required Qwen license and
attribution notice are retained in this repository.
The other checkpoints were trained by the Open-Qwen-Music project. Their terms
are described in the repository LICENSE. Third-party code and architecture
adaptations retain their respective notices.
The use of the name “Qwen” identifies the referenced method and upstream model lineage. It does not indicate affiliation with or endorsement by the Qwen team.
An independent research reproduction of the Qwen-Music method for text-to-music generation
GitHub · Dataset · Demo · Reference Paper
Open-Qwen-Music is an independent research reproduction based on the architecture and training methods described in the Qwen-Music Technical Report. It is not an official Qwen release and is not affiliated with, endorsed by, or maintained by the Qwen team or Alibaba Cloud.
The checkpoints in this repository were prepared by this project. They are not official Qwen-Music checkpoints or evaluation artifacts.
Open-Qwen-Music generates 48 kHz stereo music from text descriptions, musical tags, lyrics, and section-level structure. A music language model first produces 25 Hz semantic tokens, which are converted to audio by an acoustic renderer, spectrogram VAE, and bandwidth refiner.
| Component | Provenance |
|---|---|
| Music language model | Initialized from Qwen/Qwen2.5-Omni-3B and further trained by this project |
| Semantic tokenizer | Trained by this project following the semantic-token design described in the reference paper |
| Acoustic renderer | Trained by this project using an implementation informed by the published method and Stable Audio 3 architecture |
| Acoustic VAE | Trained by this project using the architecture documented in the source repository |
| Bandwidth refiner | Trained by this project using the implementation documented in the source repository |
The bundle contains no official Qwen-Music checkpoint. The renderer also uses
the pinned Qwen/Qwen3-Embedding-0.6B text encoder at runtime; that external
model is downloaded separately and is not included in this repository.
| Component | Purpose |
|---|---|
| Music language model | Generates semantic music tokens from the prompt |
| Semantic tokenizer | Converts reference audio into the semantic token space |
| Acoustic renderer | Generates acoustic latents from semantic tokens and text |
| Acoustic VAE | Decodes acoustic latents into a complex spectrogram |
| Bandwidth refiner | Restores high-frequency detail before waveform synthesis |
The semantic interface uses one 32,768-entry codebook at 25 Hz. The released language model uses a plain semantic-token sequence and was trained for 10,000 optimizer updates in two 5,000-update phases.
Clone the project source and install the inference dependencies:
git clone https://github.com/biang15343100-source/Open-Qwen-Music.git
cd Open-Qwen-Music
python -m venv .venv
source .venv/bin/activate
pip install -e ".[render]"
Run the complete text-to-music pipeline with the included prompt:
python scripts/infer.py \
--model oqmtest1451/open-qwen-music-weights \
--prompts examples/prompts.jsonl \
--output-dir outputs/demo \
--device cuda
The default language-model sampling temperature is 0.7. Each prompt produces
a 48 kHz stereo WAV file and a JSON metadata sidecar. See the
GitHub inference guide
for the prompt schema, offline download instructions, and runtime options.
To download the bundle in advance:
hf download oqmtest1451/open-qwen-music-weights \
--local-dir checkpoints/open-qwen-music
python scripts/infer.py \
--model checkpoints/open-qwen-music \
--prompts examples/prompts.jsonl \
--output-dir outputs/demo \
--device cuda
This implementation is inspired by the architecture and training methodology described in the Qwen-Music Technical Report by Xu et al. The paper is cited as the source of the method. Its reported experiments and results belong to the original authors and should not be interpreted as results of this reproduction.
This project uses independently prepared data, training infrastructure, checkpoints, and demonstrations. Differences in data, scale, optimization, and implementation may produce results that differ from the original report.
The training corpus is published as
david-miller-45678/open-qwen-music-dataset-c-minimax-music3.
The model bundle is tied to dataset revision
454294f27d920bb3c1430566bb7f5c153ece4c27, containing 62,417 audio records
and structured annotations in WebDataset format.
The dataset is restricted to non-commercial academic research and includes
source-specific terms. Review its LICENSE, NOTICE, source policy, and
per-record rights metadata before use.
End-to-end inference loads the language model, acoustic renderer, VAE, refiner, and text encoder. A CUDA GPU with bfloat16 support is recommended. CPU execution is intended for interface checks and is not practical for text-to-music generation.
language-model/ Music language model and text tokenizer
semantic-tokenizer/ Audio-to-semantic tokenizer
acoustic-renderer/ Acoustic diffusion transformer
acoustic-vae/ Spectrogram autoencoder
bandwidth-refiner/ High-frequency refinement model
assets/ Latent statistics and semantic embeddings
This is a research reproduction, and it should not be expected to match the original Qwen-Music system. Generated music can contain structural drift, imperfect lyric intelligibility, unstable long-range repetition, and audio artifacts. Outputs may reflect biases in the training data. Review generated audio before publication or downstream use.
This repository contains components with different provenance.
The language-model component is derived from Qwen/Qwen2.5-Omni-3B and remains
subject to the included Qwen Research License. The required Qwen license and
attribution notice are retained in this repository.
The other checkpoints were trained by the Open-Qwen-Music project. Their terms
are described in the repository LICENSE. Third-party code and architecture
adaptations retain their respective notices.
The use of the name “Qwen” identifies the referenced method and upstream model lineage. It does not indicate affiliation with or endorsement by the Qwen team.