ide8/tacotron2

Multispeaker & Emotional TTS based on Tacotron 2 and Waveglow

46
/ 100
Emerging

Embeds speaker and emotion information as discrete tokens into the synthesis pipeline, enabling fine-grained control over prosody during inference. Built on PyTorch with FP16 support and configuration-driven experiment management, supporting distributed training across multi-GPU setups. Includes integrated data preprocessing with audio normalization, speaker/emotion labeling, and loss balancing coefficients for handling imbalanced datasets.

128 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

128

Forks

26

Language

Jupyter Notebook

License

BSD-3-Clause

Last pushed

Apr 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ide8/tacotron2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.