andi611/CS-Tacotron-Pytorch
Pytorch implementation of CS-Tacotron, a code-switching speech synthesis end-to-end generative TTS model.
This project helps create natural-sounding spoken audio from text that mixes Chinese and English. You provide written text that switches between these languages, and it generates an audio file that sounds like a person speaking that mixed-language text. This is useful for anyone creating multilingual audio content, such as educators, content creators, or automated customer service providers.
No commits in the last 6 months.
Use this if you need to generate high-quality, human-like speech from text that seamlessly blends Chinese and English.
Not ideal if your primary need is for purely monolingual speech synthesis in a language other than Chinese or English, or if you need to synthesize speech from a different language pair.
Stars
23
Forks
6
Language
Python
License
MIT
Category
Last pushed
Mar 14, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/andi611/CS-Tacotron-Pytorch"
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