neverix / musicgen_trainer
simple trainer for musicgen/audiocraft
☆15Updated last year
Alternatives and similar repositories for musicgen_trainer:
Users that are interested in musicgen_trainer are comparing it to the libraries listed below
- Flexible LoRA Implementation to use with stable-audio-tools☆64Updated 6 months ago
- Unofficial implementation JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models(https://arxiv.org/abs/2308.…☆51Updated last year
- A DDSP-based neural voice synthesiser.☆113Updated 4 months ago
- ☆63Updated 11 months ago
- Code for Investigating Personalization Methods in Text to Music Generation☆36Updated 11 months ago
- ☆43Updated 9 months ago
- Unofficial download repository for MusicCaps☆46Updated last year
- Unofficial implementation JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation(https://arxiv.org/abs/2310.1…☆29Updated last year
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆40Updated last year
- Findings of ACL 2023 | AlignSTS: a speech-to-singing (STS) model based on modality disentanglement and cross-modal alignment☆66Updated 8 months ago
- [ISMIR 2023] LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT☆46Updated last year
- Robust Singing Voice Transcription and MIDI Extraction☆71Updated 3 months ago
- Audio Prompt Adapter: Unleashing music editing abilities for text-to-music with lightweight finetuning [ISMIR 2024]☆48Updated 5 months ago
- ☆30Updated last year
- AudioSR-Upsampling (any -> 48kHz)☆40Updated last year
- MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage☆40Updated 8 months ago
- Trainer for audio-diffusion-pytorch☆128Updated 2 years ago
- AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)☆95Updated 4 months ago
- [PyTorch] Minimal codebase for MusicGen models☆57Updated 2 months ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆57Updated 2 years ago
- ☆79Updated 2 years ago
- Unofficial implementation of NANSY++ in Pytorch Lightning☆50Updated last year
- Controlled audio inpainting using SD-fine tuned model Riffusion in a ControlNet Architecture☆28Updated last year
- dog-can-sing-song☆21Updated 4 months ago
- Fine-tune Stable Audio Open with DiT ControlNet.☆204Updated last month
- million song dataset split for extended clean tag & artist-level stratified☆48Updated last year
- ☆71Updated 4 months ago
- Audiogen Codec☆131Updated 8 months ago
- ☆38Updated last year