jxzhanggg/nonparaSeq2seqVC_code

Implementation code of non-parallel sequence-to-sequence VC

48
/ 100
Emerging

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.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

248

Forks

56

Language

Python

License

MIT

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.