--- license: apache-2.0 language: - en pipeline_tag: text-to-audio tags: - music_generation --- [//]: # (# InspireMusic)

logo

[//]: # (

) [//]: # ( ) [//]: # ( InspireMusic) [//]: # (

)

Demo Code Model Space Space Paper [//]: # () [//]: # ( Model) [//]: # () [//]: # ( Paper) [//]: # () [//]: # ( Githube Star) [//]: # () [//]: # ( chat on WeChat) [//]: # () [//]: # ( chat on Discord) [//]: # ( ) [//]: # ( Static Badge) [//]: # () [//]: # (Commits last month) [//]: # ( ) [//]: # ( Issues closed) [//]: # ( ) [//]: # ( Discussion posts)

InspireMusic is a fundamental AIGC toolkit and models designed for music, song, and audio generation using PyTorch. ![GitHub Repo stars](https://img.shields.io/github/stars/FunAudioLLM/InspireMusic) Please support our community project 💖 by starring it on GitHub 加⭐支持 🙏 --- ## Highlights **InspireMusic** focuses on music generation, song generation and audio generation. - A unified framework for music/song/audio generation. Controllable with text prompts, music genres, music structures, etc. - Support music generation tasks with high audio quality, with available sampling rates of 24kHz, 48kHz. - Support long-form audio generation. - Convenient fine-tuning and inference. Support mixed precision training (FP16, FP32). Provide convenient fine-tuning and inference scripts and strategies, allowing users to easily fine-tune their music generation models. ## What's New 🔥 - 2025/02: InspireMusic demo is available on [ModelScope Space](https://modelscope.cn/studios/iic/InspireMusic/summary) and [HuggingFace Space](https://huggingface.co/spaces/FunAudioLLM/InspireMusic). - 2025/01: Open-source [InspireMusic-Base](https://modelscope.cn/models/iic/InspireMusic/summary), [InspireMusic-Base-24kHz](https://modelscope.cn/models/iic/InspireMusic-Base-24kHz/summary), [InspireMusic-1.5B](https://modelscope.cn/models/iic/InspireMusic-1.5B/summary), [InspireMusic-1.5B-24kHz](https://modelscope.cn/models/iic/InspireMusic-1.5B-24kHz/summary), [InspireMusic-1.5B-Long](https://modelscope.cn/models/iic/InspireMusic-1.5B-Long/summary) models for music generation. Models are available on both ModelScope and HuggingFace. - 2024/12: Support to generate 48kHz audio with super resolution flow matching. - 2024/11: Welcome to preview 👉🏻 [**InspireMusic Demos**](https://iris2c.github.io/InspireMusic) 👈🏻. We're excited to share this with you and are working hard to bring even more features and models soon. Your support and feedback mean a lot to us! - 2024/11: We are thrilled to announce the open-sourcing of the **InspireMusic** [code repository](https://github.com/FunAudioLLM/InspireMusic) and [demos](https://iris2c.github.io/InspireMusic). **InspireMusic** is a unified framework for music, song, and audio generation, featuring capabilities such as text-to-music conversion, music structure, genre control, and timestamp management. InspireMusic stands out for its exceptional music generation and instruction-following abilities. ## Introduction > [!Note] > This repo contains the algorithm infrastructure and some simple examples. Currently only support English text prompts. > [!Tip] > To explore the performance, please refer to [InspireMusic Demo Page](https://iris2c.github.io/InspireMusic). We will open-source better & larger models soon. InspireMusic is a unified music, song and audio generation framework through the audio tokenization and detokenization process integrated with a large autoregressive transformer. The original motive of this toolkit is to empower the common users to innovate soundscapes and enhance euphony in research through music, song, and audio crafting. The toolkit provides both inference and training code for AI generative models that create high-quality music. Featuring a unified framework, InspireMusic incorporates autoregressive Transformer and conditional flow-matching modeling (CFM), allowing for the controllable generation of music, songs, and audio with both textual and structural music conditioning, as well as neural audio tokenizers. Currently, the toolkit supports text-to-music generation and plans to expand its capabilities to include text-to-song and text-to-audio generation in the future. ## InspireMusic

Light
Figure 1. An overview of the InspireMusic framework. We introduce InspireMusic, a unified framework for music, song and audio generation, capable of producing 48kHz long-form audio. InspireMusic employs an autoregressive transformer to generate music tokens in response to textual input. Complementing this, an ODE-based diffusion model, specifically flow matching, is utilized to reconstruct latent features from these generated music tokens. Then a vocoder generates audio waveforms from the reconstructed features. for input text, an ODE-based diffusion model, flow matching, to reconstruct latent features from the generated music tokens, and a vocoder to generate audio waveforms. InspireMusic is capable of text-to-music, music continuation, music reconstruction, and music super resolution tasks. It employs WavTokenizer as an audio tokenizer to convert 24kHz audio into 75Hz discrete tokens, while HifiCodec serves as a music tokenizer, transforming 48kHz audio into 150Hz latent features compatible with the flow matching model.

## Installation ### Clone - Clone the repo ``` sh git clone --recursive https://github.com/FunAudioLLM/InspireMusic.git # If you failed to clone submodule due to network failures, please run the following command until success cd InspireMusic git submodule update --init --recursive ``` ### Install InspireMusic requires Python 3.8, PyTorch 2.0.1. To install InspireMusic, you can run one of the following: - Install Conda: please see https://docs.conda.io/en/latest/miniconda.html - Create Conda env: ``` sh conda create -n inspiremusic python=3.8 conda activate inspiremusic cd InspireMusic # pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platforms. conda install -y -c conda-forge pynini==2.1.5 pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com # install flash attention to speedup training, support version 2.6.3 pip install flash-attn --no-build-isolation ``` Currently support on CUDA Version 11.x. - Install within the package: ```sh cd InspireMusic # You can run to install the packages python setup.py install pip install flash-attn --no-build-isolation ``` We also recommend having `sox` or `ffmpeg` installed, either through your system or Anaconda: ```sh # # Install sox # ubuntu sudo apt-get install sox libsox-dev # centos sudo yum install sox sox-devel # Install ffmpeg # ubuntu sudo apt-get install ffmpeg # centos sudo yum install ffmpeg ``` ### Quick Start Here is a quick example inference script for music generation. ``` sh cd InspireMusic mkdir -p pretrained_models # Download models # ModelScope git clone https://www.modelscope.cn/iic/InspireMusic-1.5B-Long.git pretrained_models/InspireMusic-1.5B-Long # HuggingFace git clone https://huggingface.co/FunAudioLLM/InspireMusic-1.5B-Long.git pretrained_models/InspireMusic-1.5B-Long cd examples/music_generation # run a quick inference example bash infer_1.5b_long.sh ``` Here is a quick start running script to run music generation task including data preparation pipeline, model training, inference. ``` sh cd InspireMusic/examples/music_generation/ bash run.sh ``` ### One-line Inference #### Text-to-music Task One-line Shell script for text-to-music task. ``` sh cd examples/music_generation # with flow matching # use one-line command to get a quick try python -m inspiremusic.cli.inference # custom the config like the following one-line command python -m inspiremusic.cli.inference --task text-to-music -m "InspireMusic-1.5B-Long" -g 0 -t "Experience soothing and sensual instrumental jazz with a touch of Bossa Nova, perfect for a relaxing restaurant or spa ambiance." -c intro -s 0.0 -e 30.0 -r "exp/inspiremusic" -o output -f wav # without flow matching python -m inspiremusic.cli.inference --task text-to-music -g 0 -t "Experience soothing and sensual instrumental jazz with a touch of Bossa Nova, perfect for a relaxing restaurant or spa ambiance." --fast True ``` Alternatively, you can run the inference with just a few lines of Python code. ```python from inspiremusic.cli.inference import InspireMusicUnified from inspiremusic.cli.inference import set_env_variables if __name__ == "__main__": set_env_variables() model = InspireMusicUnified(model_name = "InspireMusic-1.5B-Long") model.inference("text-to-music", "Experience soothing and sensual instrumental jazz with a touch of Bossa Nova, perfect for a relaxing restaurant or spa ambiance.") ``` #### Music Continuation Task One-line Shell script for music continuation task. ``` sh cd examples/music_generation # with flow matching python -m inspiremusic.cli.inference --task continuation -g 0 -a audio_prompt.wav # without flow matching python -m inspiremusic.cli.inference --task continuation -g 0 -a audio_prompt.wav --fast True ``` Alternatively, you can run the inference with just a few lines of Python code. ```python from inspiremusic.cli.inference import InspireMusicUnified from inspiremusic.cli.inference import set_env_variables if __name__ == "__main__": set_env_variables() model = InspireMusicUnified(model_name = "InspireMusic-1.5B-Long") # just use audio prompt model.inference("continuation", None, "audio_prompt.wav") # use both text prompt and audio prompt model.inference("continuation", "Continue to generate jazz music.", "audio_prompt.wav") ``` ## Models ### Download Model We strongly recommend that you download our pretrained `InspireMusic model`. If you are an expert in this field, and you are only interested in training your own InspireMusic model from scratch, you can skip this step. ``` sh # git模型下载，请确保已安装git lfs mkdir -p pretrained_models git clone https://www.modelscope.cn/iic/InspireMusic-1.5B-Long.git pretrained_models/InspireMusic ``` ### Available Models Currently, we open source the music generation models support 24KHz mono and 48KHz stereo audio. The table below presents the links to the ModelScope and Huggingface model hub. More models will be available soon. | Model name | Model Links | Remarks | |---------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------| | InspireMusic-Base-24kHz | [![model](https://img.shields.io/badge/ModelScope-Model-green.svg)](https://modelscope.cn/models/iic/InspireMusic-Base-24kHz/summary) [![model](https://img.shields.io/badge/HuggingFace-Model-green.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-Base-24kHz) | Pre-trained Music Generation Model, 24kHz mono, 30s | | InspireMusic-Base | [![model](https://img.shields.io/badge/ModelScope-Model-green.svg)](https://modelscope.cn/models/iic/InspireMusic/summary) [![model](https://img.shields.io/badge/HuggingFace-Model-green.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-Base) | Pre-trained Music Generation Model, 48kHz, 30s | | InspireMusic-1.5B-24kHz | [![model](https://img.shields.io/badge/ModelScope-Model-green.svg)](https://modelscope.cn/models/iic/InspireMusic-1.5B-24kHz/summary) [![model](https://img.shields.io/badge/HuggingFace-Model-green.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-1.5B-24kHz) | Pre-trained Music Generation 1.5B Model, 24kHz mono, 30s | | InspireMusic-1.5B | [![model](https://img.shields.io/badge/ModelScope-Model-green.svg)](https://modelscope.cn/models/iic/InspireMusic-1.5B/summary) [![model](https://img.shields.io/badge/HuggingFace-Model-green.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-1.5B) | Pre-trained Music Generation 1.5B Model, 48kHz, 30s | | InspireMusic-1.5B-Long ⭐ | [![model](https://img.shields.io/badge/ModelScope-Model-green.svg)](https://modelscope.cn/models/iic/InspireMusic-1.5B-Long/summary) [![model](https://img.shields.io/badge/HuggingFace-Model-green.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-1.5B-Long) | Pre-trained Music Generation 1.5B Model, 48kHz, support long-form music generation more than 5mins | | InspireSong-1.5B | [![model](https://img.shields.io/badge/ModelScope-Model-lightgrey.svg)]() [![model](https://img.shields.io/badge/HuggingFace-Model-lightgrey.svg)]() | Pre-trained Song Generation 1.5B Model, 48kHz stereo | | InspireAudio-1.5B | [![model](https://img.shields.io/badge/ModelScope-Model-lightgrey.svg)]() [![model](https://img.shields.io/badge/HuggingFace-Model-lightgrey.svg)]() | Pre-trained Audio Generation 1.5B Model, 48kHz stereo | | Wavtokenizer[[1]](https://openreview.net/forum?id=yBlVlS2Fd9) (75Hz) | [![model](https://img.shields.io/badge/ModelScope-Model-green.svg)](https://modelscope.cn/models/iic/InspireMusic-1.5B-Long/file/view/master?fileName=wavtokenizer%252Fmodel.pt) [![model](https://img.shields.io/badge/HuggingFace-Model-green.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-1.5B-Long/tree/main/wavtokenizer) | An extreme low bitrate audio tokenizer for music with one codebook at 24kHz audio. | | Music_tokenizer (75Hz) | [![model](https://img.shields.io/badge/ModelScope-Model-green.svg)](https://modelscope.cn/models/iic/InspireMusic-1.5B-24kHz/file/view/master?fileName=music_tokenizer%252Fmodel.pt) [![model](https://img.shields.io/badge/HuggingFace-Model-green.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-1.5B-24kHz/tree/main/music_tokenizer) | A music tokenizer based on HifiCodec[2] at 24kHz audio. | | Music_tokenizer (150Hz) | [![model](https://img.shields.io/badge/ModelScope-Model-green.svg)](https://modelscope.cn/models/iic/InspireMusic-1.5B-Long/file/view/master?fileName=music_tokenizer%252Fmodel.pt) [![model](https://img.shields.io/badge/HuggingFace-Model-green.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-1.5B-Long/tree/main/music_tokenizer) | A music tokenizer based on HifiCodec at 48kHz audio. | ## Basic Usage At the moment, InspireMusic contains the training code and inference code for [music generation](https://github.com/FunAudioLLM/InspireMusic/tree/main/examples/music_generation). More tasks such as song generation and audio generation will be supported in future. ### Training Here is an example to train LLM model, support FP16 training. ```sh torchrun --nnodes=1 --nproc_per_node=8 \ --rdzv_id=1024 --rdzv_backend="c10d" --rdzv_endpoint="localhost:0" \ inspiremusic/bin/train.py \ --train_engine "torch_ddp" \ --config conf/inspiremusic.yaml \ --train_data data/train.data.list \ --cv_data data/dev.data.list \ --model llm \ --model_dir `pwd`/exp/music_generation/llm/ \ --tensorboard_dir `pwd`/tensorboard/music_generation/llm/ \ --ddp.dist_backend "nccl" \ --num_workers 8 \ --prefetch 100 \ --pin_memory \ --deepspeed_config ./conf/ds_stage2.json \ --deepspeed.save_states model+optimizer \ --fp16 ``` Here is an example code to train flow matching model, does not support FP16 training. ```sh torchrun --nnodes=1 --nproc_per_node=8 \ --rdzv_id=1024 --rdzv_backend="c10d" --rdzv_endpoint="localhost:0" \ inspiremusic/bin/train.py \ --train_engine "torch_ddp" \ --config conf/inspiremusic.yaml \ --train_data data/train.data.list \ --cv_data data/dev.data.list \ --model flow \ --model_dir `pwd`/exp/music_generation/flow/ \ --tensorboard_dir `pwd`/tensorboard/music_generation/flow/ \ --ddp.dist_backend "nccl" \ --num_workers 8 \ --prefetch 100 \ --pin_memory \ --deepspeed_config ./conf/ds_stage2.json \ --deepspeed.save_states model+optimizer ``` ### Inference Here is an example script to quickly do model inference. ``` sh cd InspireMusic/examples/music_generation/ bash infer.sh ``` Here is an example code to run inference with normal mode, i.e., with flow matching model for text-to-music and music continuation tasks. ```sh pretrained_model_dir = "./pretrained_models/InspireMusic/" for task in 'text-to-music' 'continuation'; do python inspiremusic/bin/inference.py --task $task \ --gpu 0 \ --config conf/inspiremusic.yaml \ --prompt_data data/test/parquet/data.list \ --flow_model $pretrained_model_dir/flow.pt \ --llm_model $pretrained_model_dir/llm.pt \ --music_tokenizer $pretrained_model_dir/music_tokenizer \ --wavtokenizer $pretrained_model_dir/wavtokenizer \ --result_dir `pwd`/exp/inspiremusic/${task}_test \ --chorus verse \ --min_generate_audio_seconds 8 \ --max_generate_audio_seconds 30 done ``` Here is an example code to run inference with fast mode, i.e., without flow matching model for text-to-music and music continuation tasks. ```sh pretrained_model_dir = "./pretrained_models/InspireMusic/" for task in 'text-to-music' 'continuation'; do python inspiremusic/bin/inference.py --task $task \ --gpu 0 \ --config conf/inspiremusic.yaml \ --prompt_data data/test/parquet/data.list \ --flow_model $pretrained_model_dir/flow.pt \ --llm_model $pretrained_model_dir/llm.pt \ --music_tokenizer $pretrained_model_dir/music_tokenizer \ --wavtokenizer $pretrained_model_dir/wavtokenizer \ --result_dir `pwd`/exp/inspiremusic/${task}_test \ --chorus verse \ --fast \ --min_generate_audio_seconds 8 \ --max_generate_audio_seconds 30 done ``` ## Disclaimer The content provided above is for academic purposes only and is intended to demonstrate technical capabilities. Some examples are sourced from the internet. If any content infringes on your rights, please contact us to request its removal.