Alternatives and similar repositories for SingMOS

Users that are interested in SingMOS are comparing it to the libraries listed below

• RickyL-2000 / ROSVOT
  Robust Singing Voice Transcription and MIDI Extraction
  ☆98Updated last year
• gwx314 / STARS
  STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation
  ☆60Updated last month
• haoheliu / SemantiCodec
  ☆45Updated last year
• qiuqiangkong / audio_flow
  ☆110Updated 3 months ago
• FlyToYourMooN / DDPM-Midi2Performance-Model
  Music generation
  ☆24Updated last year
• RickyL-2000 / AlignSTS
  Findings of ACL 2023 | AlignSTS: a speech-to-singing (STS) model based on modality disentanglement and cross-modal alignment
  ☆68Updated last year
• AMAAI-Lab / JamendoMaxCaps
  JamendoMaxCaps is a large-scale dataset of 362,000 instrumental creative commons tracks
  ☆44Updated 6 months ago
• WX-Wei / HarmoF0
  ☆107Updated last year
• OpenNSP / Hifi-vaegan
  ☆47Updated last year
• lesterphillip / serenade
  A Singing Style Conversion Framework Based On Audio Infilling
  ☆30Updated 7 months ago
• SonyCSLParis / ssl-singer-identity
  ☆60Updated 2 years ago
• xiquan-li / MeanAudio
  MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows
  ☆114Updated 3 months ago
• innnky / descript-audio-vae
  VAE modified from Descript Audio Codec, which replaces the RVQ with VAE
  ☆84Updated last year
• MWM-io / nansypp
  Unofficial implementation of NANSY++ in Pytorch Lightning
  ☆50Updated last year
• YoonjinXD / kadtk
  A standardized toolkit of Kernel Audio Distance (KAD)—a distribution-free, unbiased, and computationally efficient metric for evaluating …
  ☆92Updated 6 months ago
• vtuber-plan / NSF-HiFiGAN
  Vocoder NSF-HiFiGAN (Moved into deepaudio)
  ☆55Updated 3 years ago
• ASLP-lab / SongFormer
  ☆68Updated last month
• 0417keito / JEN-1-pytorch
  Unofficial implementation JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models(https://arxiv.org/abs/2308.…
  ☆54Updated last year
• yukara-ikemiya / floss-torch
  PyTorch implementation of "Source Separation by Flow Matching (FLOSS)" by Google DeepMind
  ☆83Updated 3 weeks ago
• yxlllc / pc-ddsp
  Pitch Controllable DDSP Vocoders
  ☆77Updated last year
• freds0 / free-svc
  [ICASSP 2025] FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion
  ☆87Updated 4 months ago
• MTG / omar-rq
  Training, validation, and inference code for various SSL approaches and architectures.
  ☆70Updated last month
• iamycy / golf
  A DDSP-based neural voice synthesiser.
  ☆123Updated last year
• sanderwood / melodyt5
  MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing [ISMIR 2024]
  ☆44Updated 10 months ago
• lars76 / swift-f0
  Fast and accurate fundamental frequency (F0) detector using convolutional neural networks
  ☆101Updated 3 months ago
• zengchang233 / xiaoicesing2
  The source code for the paper XiaoiceSing2 (interspeech2023)
  ☆48Updated last year
• crlandsc / torch-log-wmse
  logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source…
  ☆44Updated 7 months ago
• haiciyang / LaDiffCodec
  ICASSP 2024 - Generative De-Quantization for Neural Speech Codec via Latent Diffusion.
  ☆55Updated 3 weeks ago
• alobashev / mkl-vc
  [Interspeech 2025] Official implementation of "Training-Free Voice Conversion with Factorized Optimal Transport"
  ☆43Updated 2 months ago
• chenjianyi / fastsag
  FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation
  ☆27Updated 11 months ago