Yangyangii/TPGST-Tacotron
Google's TPGST reimplementation.
This project helps you create natural-sounding spoken audio from written Korean text, capturing different expressive styles. You provide Korean text and a dataset of Korean speech recordings, and it generates audio files of that text being spoken. This is ideal for voice-over artists, content creators, or anyone needing to generate expressive Korean speech.
No commits in the last 6 months.
Use this if you need to transform written Korean text into speech that conveys specific emotions or speaking styles.
Not ideal if you need to generate speech in languages other than Korean, or if you require an integrated vocoder to immediately listen to the output.
Stars
34
Forks
8
Language
Python
License
—
Category
Last pushed
Dec 11, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Yangyangii/TPGST-Tacotron"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bshall/Tacotron
A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Kyubyong/dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
DemisEom/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Rayhane-mamah/Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model