yl4579/PL-BERT
Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions
This project helps improve the naturalness and rhythm of computer-generated speech. It takes text as input and helps Text-to-Speech (TTS) systems produce speech that sounds more human-like, especially for phrases or sentences that are out of the ordinary. Anyone developing or fine-tuning advanced Text-to-Speech models, particularly researchers or engineers focused on speech synthesis quality, would use this.
268 stars. No commits in the last 6 months.
Use this if you are a speech synthesis researcher or engineer looking to enhance the prosody (rhythm, stress, and intonation) of your Text-to-Speech models, particularly for generating natural-sounding speech from diverse or out-of-distribution text.
Not ideal if you are an end-user simply looking to generate basic text-to-speech output without diving into model architecture modifications or fine-tuning.
Stars
268
Forks
57
Language
Python
License
MIT
Category
Last pushed
Jan 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yl4579/PL-BERT"
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...
jxzhanggg/nonparaSeq2seqVC_code
Implementation code of non-parallel sequence-to-sequence VC