neosapience/mlp-singer
Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis (IEEE MLSP 2021)
Implements a non-autoregressive, attention-free MLP-based architecture inspired by MLP-Mixer for parallel mel-spectrogram generation, achieving 200× real-time factor on CPU and 3400× on GPU. Requires input triplets of MIDI transcriptions, lyrics text, and monophonic audio; integrates HiFi-GAN as the neural vocoder backend for waveform generation, with support for alternative vocoders like WaveGlow.
118 stars. No commits in the last 6 months.
Stars
118
Forks
26
Language
Python
License
MIT
Category
Last pushed
Feb 24, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/neosapience/mlp-singer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowTTS
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for...
lucasnewman/nanospeech
A simple, hackable text-to-speech system in PyTorch and MLX
Tomiinek/Multilingual_Text_to_Speech
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing,...
jxzhanggg/nonparaSeq2seqVC_code
Implementation code of non-parallel sequence-to-sequence VC
keonlee9420/STYLER
Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech...