Skip to content

PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model

License

Notifications You must be signed in to change notification settings

Text-to-Audio/Make-An-Audio

Repository files navigation

Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models

Rongjie Huang, Jiawei Huang, Dongchao Yang, Yi Ren, Luping Liu, Mingze Li, Zhenhui Ye, Jinglin Liu, Xiang Yin, Zhou Zhao

PyTorch Implementation of Make-An-Audio (ICML'23): a conditional diffusion probabilistic model capable of generating high fidelity audio efficiently from X modality.

arXiv Hugging Face GitHub Stars

We provide our implementation and pretrained models as open source in this repository.

Visit our demo page for audio samples.

Text-to-Audio HuggingFace Space | Audio Inpainting HuggingFace Space

News

Quick Started

We provide an example of how you can generate high-fidelity samples using Make-An-Audio.

To try on your own dataset, simply clone this repo in your local machine provided with NVIDIA GPU + CUDA cuDNN and follow the below instructions.

Support Datasets and Pretrained Models

Simply run following command to download the weights from Google drive. Download CLAP weights from Hugging Face.

Download:
    maa1_full.ckpt and put it into ./useful_ckpts  
    BigVGAN vocoder and put it into ./useful_ckpts  
    CLAP_weights_2022.pth and put it into ./useful_ckpts/CLAP

The directory structure should be:

useful_ckpts/
├── bigvgan
│   ├── args.yml
│   └── best_netG.pt
├── CLAP
│   ├── config.yml
│   └── CLAP_weights_2022.pth
└── maa1_full.ckpt

Dependencies

See requirements in requirement.txt:

Inference with pretrained model

python gen_wav.py --prompt "a bird chirps" --ddim_steps 100 --duration 10 --scale 3 --n_samples 1 --save_name "results"

Train

dataset preparation

We can't provide the dataset download link for copyright issues. We provide the process code to generate melspec.
Before training, we need to construct the dataset information into a tsv file, which includes name (id for each audio), dataset (which dataset the audio belongs to), audio_path (the path of .wav file),caption (the caption of the audio) ,mel_path (the processed melspec file path of each audio). We provide a tsv file of audiocaps test set: ./data/audiocaps_test.tsv as a sample.

generate the melspec file of audio

Assume you have already got a tsv file to link each caption to its audio_path, which mean the tsv_file have "name","audio_path","dataset" and "caption" columns in it. To get the melspec of audio, run the following command, which will save mels in ./processed

python preprocess/mel_spec.py --tsv_path tmp.tsv --num_gpus 1 --max_duration 10

Train variational autoencoder

Assume we have processed several datasets, and save the .tsv files in data/*.tsv . Replace data.params.spec_dir_path with the data(the directory that contain tsvs) in the config file. Then we can train VAE with the following command. If you don't have 8 gpus in your machine, you can replace --gpus 0,1,...,gpu_nums

python main.py --base configs/train/vae.yaml -t --gpus 0,1,2,3,4,5,6,7

The training result will be save in ./logs/

train latent diffsuion

After Trainning VAE, replace model.params.first_stage_config.params.ckpt_path with your trained VAE checkpoint path in the config file. Run the following command to train Diffusion model

python main.py --base configs/train/diffusion.yaml -t  --gpus 0,1,2,3,4,5,6,7

The training result will be save in ./logs/

Evaluation

generate audiocaps samples

python gen_wavs_by_tsv.py --tsv_path data/audiocaps_test.tsv --save_dir audiocaps_gen

calculate FD,FAD,IS,KL

install audioldm_eval by

git clone [email protected]:haoheliu/audioldm_eval.git

Then test with:

python scripts/test.py --pred_wavsdir {the directory that saves the audios you generated} --gt_wavsdir {the directory that saves audiocaps test set waves}

calculate Clap_score

python wav_evaluation/cal_clap_score.py --tsv_path {the directory that saves the audios you generated}/result.tsv

X-To-Audio

Audio2Audio

python scripts/audio2audio.py  --prompt "a bird chirping"  --strength 0.3 --init-audio sample.wav --ckpt useful_ckpts/maa1_full.ckpt --vocoder_ckpt useful_ckpts/bigvgan --config configs/text_to_audio/txt2audio_args.yaml --outdir audio2audio_samples

Acknowledgements

This implementation uses parts of the code from the following Github repos: CLAP, Stable Diffusion, as described in our code.

Citations

If you find this code useful in your research, please consider citing:

@article{huang2023make,
  title={Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models},
  author={Huang, Rongjie and Huang, Jiawei and Yang, Dongchao and Ren, Yi and Liu, Luping and Li, Mingze and Ye, Zhenhui and Liu, Jinglin and Yin, Xiang and Zhao, Zhou},
  journal={arXiv preprint arXiv:2301.12661},
  year={2023}
}

Disclaimer

Any organization or individual is prohibited from using any technology mentioned in this paper to generate someone's speech without his/her consent, including but not limited to government leaders, political figures, and celebrities. If you do not comply with this item, you could be in violation of copyright laws.

About

PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages