A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)
-
Updated
Apr 2, 2023 - Python
#
diffsinger
Here are 9 public repositories matching this topic...
PyTorch implementation of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (focused on DiffSpeech)
text-to-speech pytorch tts speech-synthesis english diffusion singing-voice diffusion-models neural-tts non-autoregressive fastspeech ddpm diffsinger
-
Updated
Feb 3, 2022 - Python
Singing Voice Synthesis based on VITS, different from VISinger
speech-synthesis svs singing-synthesis singing-voice-synthesis vits diffsinger opencpop vits-svs visinger
-
Updated
Nov 13, 2023 - Python
Multispeaker Community Vocoder Model for DiffSinger
-
Updated
May 4, 2024 - Python
-
Updated
Dec 30, 2022 - Python
A fork of genon2nnsvs with modifications made for english speakers and diffsinger users
-
Updated
Jul 16, 2024 - Python
Convert the UTAU Voicebank to a configuration compatible with DiffSinger Dataset
-
Updated
Mar 2, 2025 - Python
A Streamlit-based web application that converts Japanese text (romaji/hiragana/katakana) into MIDI files with customizable parameters. Perfect for UTAU/DIFFSINGER and other voice synthesis development workflows.
-
Updated
Dec 4, 2024 - Python
Improve this page
Add a description, image, and links to the diffsinger topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the diffsinger topic, visit your repo's landing page and select "manage topics."