cvqluu/Factorized-TDNN
PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
Implements 3-stage splicing convolutions with semi-orthogonal constraints enforced via post-SGD updates, closely mirroring Kaldi's nnet3 `ConstrainOrthonormalInternal`. Includes modular `SOrthConv` and `FTDNNLayer` components for speaker embedding tasks, plus SharedDimScaleDropout for time-correlated regularization across sequences.
149 stars. No commits in the last 6 months.
Stars
149
Forks
34
Language
Python
License
MIT
Category
Last pushed
Jan 06, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/cvqluu/Factorized-TDNN"
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