#6262nd of 68 in Training and fine-tuningFor voice, speech and music

stable-audio-tools

Training and inference code for diffusion-based audio generation models

Stars
3.9k
License
MIT
Last commit
May 2026
Language
Python
Stars, last 29 weeks+264
25 Apr 2026: 3,651 stars2 May 2026: 3,662 stars9 May 2026: 3,671 stars16 May 2026: 3,679 stars23 May 2026: 3,710 stars30 May 2026: 3,736 stars6 Jun 2026: 3,745 stars13 Jun 2026: 3,755 stars20 Jun 2026: 3,766 stars27 Jun 2026: 3,780 stars4 Jul 2026: 3,790 stars11 Jul 2026: 3,799 stars18 Jul 2026: 3,805 stars25 Jul 2026: 3,816 stars1 Aug 2026: 3,821 stars8 Aug 2026: 3,828 stars15 Aug 2026: 3,832 stars22 Aug 2026: 3,838 stars29 Aug 2026: 3,844 stars5 Sept 2026: 3,848 stars12 Sept 2026: 3,852 stars19 Sept 2026: 3,858 stars26 Sept 2026: 3,864 stars3 Oct 2026: 3,868 stars10 Oct 2026: 3,874 stars17 Oct 2026: 3,886 stars24 Oct 2026: 3,894 stars31 Oct 2026: 3,899 stars7 Nov 2026: 3,904 stars14 Nov 2026: 3,915 stars

3,651 on 25 Apr 20263,915 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

PyTorch Lightning codebase from Stability AI for training, fine-tuning and running audio generation models, configured through JSON model and dataset files. It supports autoencoder, unconditional and conditional diffusion, inpainting, diffusion autoencoder and LM model types. A basic Gradio interface can load pretrained checkpoints such as stable-audio-open-1.0 from Hugging Face.

Who it is for: Researchers and engineers training or fine-tuning audio generation models

Strengths

  • Training, fine-tuning and inference in one repo, driven by JSON configs
  • Multi-GPU and multi-node training via PyTorch Lightning, with DeepSpeed ZeRO Stage 2 option
  • Datasets from local audio directories or WebDataset on Amazon S3
  • Unwrap script strips training state to produce smaller inference checkpoints

Weaknesses

  • Training logs to Weights & Biases, which needs an account and login
  • Gradio UI is described as basic, meant for testing models
  • Stable Audio Open weights require accepting terms on Hugging Face
  • Needs PyTorch 2.5+; Flash Attention must be installed separately

What it needs

  • Needs PyTorch 2.5+, PyTorch Lightning, Weights & Biases (training), Gradio (UI), Flash Attention (recommended), uv
  • Models: stabilityai/stable-audio-open-1.0, autoencoder, diffusion_uncond, diffusion_cond, diffusion_cond_inpaint

Also in Training and fine-tuning

See all 68
Also in Training and fine-tuning
RankProjectScore
1peftPython library for LoRA and other parameter-efficient fine-tuning of Transformers models Live demo ↗ (opens in a new tab)21.9k starsApache-2.089 out of 100
2unslothDesktop and web app to run and fine-tune local models Live demo ↗ (opens in a new tab)79.7k starsApache-2.088 out of 100
3trlPost-training library with SFT, DPO, GRPO and KTO trainers19.8k starsApache-2.088 out of 100
#4deepspeedPyTorch library for distributed training of very large models with ZeRO43.3k starsApache-2.087 out of 100
#5megatron-lmDistributed training library for large transformer models on NVIDIA GPUs18.4k starscustom license86 out of 100