keonlee9420/Parallel-Tacotron2
PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Implements differentiable duration modeling through soft-DTW loss and learned upsampling for parallel mel-spectrogram generation, eliminating autoregressive decoding bottlenecks. Integrates fairseq's `LConvBlock` components and adapts FastSpeech2's training pipeline (optimizer, scheduler, FFT blocks) while customizing soft-DTW with CUDA acceleration for GPU efficiency. Supports LJSpeech dataset preprocessing and includes TensorBoard logging; currently optimizing convergence through architectural refinements like sinusoidal positional embeddings and normalized activation patterns.
191 stars. No commits in the last 6 months.
Stars
191
Forks
44
Language
Python
License
MIT
Category
Last pushed
Nov 18, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Parallel-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