keonlee9420/Stepwise_Monotonic_Multihead_Attention
PyTorch Implementation of Stepwise Monotonic Multihead Attention similar to Enhancing Monotonicity for Robust Autoregressive Transformer TTS
This project helps create high-quality text-to-speech (TTS) systems by improving how spoken audio aligns with input text. It takes text encodings and mel-spectrogram encodings, then produces a text-audio fusion where the spoken words accurately match the original text. This is designed for engineers and researchers building robust neural TTS models.
No commits in the last 6 months.
Use this if you are developing an autoregressive text-to-speech system and need to ensure a strong, consistent alignment between the input text and the generated speech's mel-spectrogram.
Not ideal if your task does not involve sequence-to-sequence alignment for speech synthesis, as it's specifically tailored for text-to-audio matching.
Stars
39
Forks
5
Language
Python
License
MIT
Category
Last pushed
May 16, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Stepwise_Monotonic_Multihead_Attention"
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/dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
DemisEom/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Rayhane-mamah/Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model