ide8/tacotron2
Multispeaker & Emotional TTS based on Tacotron 2 and Waveglow
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.
Stars
128
Forks
26
Language
Jupyter Notebook
License
BSD-3-Clause
Category
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.
Higher-rated alternatives
bshall/Tacotron
A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
Rayhane-mamah/Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
DemisEom/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Kyubyong/dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model