haoheliu/AudioLDM-training-finetuning

AudioLDM training, finetuning, evaluation and inference.

41
/ 100
Emerging

Builds on latent diffusion architecture with integrated AudioMAE and CLAP encoders for text-to-audio generation, leveraging VAE compression and HiFiGAN vocoding at multiple sample rates. Supports custom dataset training without preprocessing via automatic resampling and segmentation, with built-in evaluation metrics for generated audio quality assessment. Compatible with both medium and small model variants, enabling efficient finetuning from pretrained checkpoints on AudioCaps or user-defined datasets.

297 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

297

Forks

58

Language

Python

License

MIT

Last pushed

Dec 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/haoheliu/AudioLDM-training-finetuning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.