jxzhanggg/nonparaSeq2seqVC_code
Implementation code of non-parallel sequence-to-sequence VC
Disentangles linguistic content from speaker identity using a sequence-to-sequence architecture, enabling voice conversion without paired training data. The model supports both text-to-speech and mel-spectrogram-based voice conversion modes through a pre-training and fine-tuning pipeline in PyTorch. Built on foundations from Tacotron2 and DeepVoice3, it extracts phoneme and spectral features from datasets like VCTK and CMU-ARCTIC for training.
248 stars. No commits in the last 6 months.
Stars
248
Forks
56
Language
Python
License
MIT
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jxzhanggg/nonparaSeq2seqVC_code"
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,...
keonlee9420/STYLER
Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech...
yl4579/PL-BERT
Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions