Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Paper
•
1910.10288
•
Published
Tacotron2-DCA (English, Sam)
American English, non-binary single-speaker Tacotron2 TTS model trained with dynamic convolutional attention (DCA) on Accenture's Sam dataset.
Trained by @erogol 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/en/sam/tacotron2-DCA')
tts.tts_to_file("Hello world", file_path="output.wav")
- Downloads last month
- 46