E2-TTS in Pytorch
Project description
E2 TTS - Pytorch (wip)
Implementation of E2-TTS, Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS, in Pytorch
You can chat with other researchers about this work here
Usage
import torch
from e2_tts_pytorch import (
E2TTS,
DurationPredictor
)
duration_predictor = DurationPredictor(
transformer = dict(
dim = 512,
depth = 2,
)
)
x = torch.randn(1, 1024, 512)
duration = torch.randn(1,)
loss = duration_predictor(x, target_duration = duration)
loss.backward()
e2tts = E2TTS(
duration_predictor = duration_predictor,
transformer = dict(
dim = 512,
depth = 4,
skip_connect_type = 'concat'
),
)
loss = e2tts(x)
loss.backward()
sampled = e2tts.sample(x)
Citations
@inproceedings{Eskimez2024E2TE,
title = {E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS},
author = {Sefik Emre Eskimez and Xiaofei Wang and Manthan Thakker and Canrun Li and Chung-Hsien Tsai and Zhen Xiao and Hemin Yang and Zirun Zhu and Min Tang and Xu Tan and Yanqing Liu and Sheng Zhao and Naoyuki Kanda},
year = {2024},
url = {https://api.semanticscholar.org/CorpusID:270738197}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
e2_tts_pytorch-0.0.1.tar.gz
(173.7 kB
view hashes)
Built Distribution
Close
Hashes for e2_tts_pytorch-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 30e6596050260fa55ceeb399292c964af67555ddd52e955ec23ce42383c9ece9 |
|
MD5 | 81870db25b8d182ae06d4df52d197d4e |
|
BLAKE2b-256 | cec67e2cd74cc0e4b8cb8918b45bcca6716a47b992fda1ad2a60c47c1557ad96 |