A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
- diffusion-models
- flow-matching
- python
- speech-synthesis
89,572 visible repositories in the index
1–3 of 3 · Most stars
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
A Elixir library for translating between hiragana, katakana, romaji, kanji and sound. It uses Mecab.
A Elixir library for translating between hiragana, katakana, romaji and sound.