5 Years of Text-to-Speech ML
cookietts. [Last Updated 2021] TTS from Cookie. Messy and experimental!
43podcast_rss_feeds. List of Podcast Feeds using iTunes API and script to download 6,000,000~ hours of English speech.
31pngnw_bert. Unofficial PyTorch implementation of PnG BERT with some changes
9pag-tacotron2. [NOT-in-Progress] PyTorch implementation of "Pre-Alignment Guided Attention for Improving Training Efficiency and Model Stability in End-to-End Speech Synthesis"
9VocoderComparisons. Train/test a variety of open source vocoders using the same input features and dataset. Then infer together for easy side-by-side comparisons.
6codedump. Somewhere to dump code
5tacotron2. Tacotron 2 - PyTorch implementation with faster-than-realtime inference
5papers.
5paint-with-words-sd. Unofficial Implementation of Paint-with-words, method from eDiffi that let you generate image from text-labeled segmentation map.
4fimfic_quote_attribution. [On Hiatus] Label FimFiction stories for AI Audiodrama generation
3Voice-Cloning-App. A Python/Pytorch app for easily synthesising human voices
2ideas.
2DiffSVC_inference_only. Contains inference code for DiffSVC unofficial reimplementation
2derpy-score-predictor. Pytorch - Predict the quality of a derpibooru image given its tags and datetime.
1podcast_wds. PyTorch Code to stream Webdataset Format Podcasts Dataset
1mimic2. Text to Speech engine based on the Tacotron architecture, initially implemented by Keith Ito.
1