Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Paper • 1803.09017 • Published
Tacotron2-DDC-GST (Chinese, M-AILABS)
Mandarin Chinese, female single-speaker Tacotron2 TTS model trained with double decoder consistency (DDC) and global style tokens (GST) on the Baker dataset.
Trained by @kirianguiller and originally published at: https://github.com/coqui-ai/TTS/releases/v0.6.1_models/
Usage
With Coqui TTS:
from TTS.api import TTS
tts = TTS('tts_models/zh-CN/baker/tacotron2-DDC-GST')
tts.tts_to_file("你好", file_path="output.wav")
- Downloads last month
- 30