Stars
- All languages
- Assembly
- AutoHotkey
- AutoIt
- Awk
- Batchfile
- Bikeshed
- C
- C#
- C++
- CMake
- CSS
- Clojure
- CoffeeScript
- Crystal
- Cuda
- Cython
- D
- Dart
- Dockerfile
- Elixir
- Fluent
- GDScript
- Go
- Groovy
- HCL
- HLSL
- HTML
- Handlebars
- Haxe
- HolyC
- Inno Setup
- JSON
- Jai
- Java
- JavaScript
- Jinja
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Less
- Lua
- M4
- MATLAB
- MDX
- Makefile
- Markdown
- Meson
- NSIS
- Nim
- Nix
- OCaml
- Objective-C++
- PHP
- PLpgSQL
- Pascal
- Perl
- PowerShell
- Python
- QML
- Red
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Smali
- Smarty
- Solidity
- Stylus
- Svelte
- Swift
- Tcl
- TeX
- TypeScript
- V
- VBScript
- Vala
- Vim Script
- Visual Basic
- Vue
- WebAssembly
- Wren
- Zig
- sed
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions
neurlang / NumToWordsGo
Forked from yousifnimah/NumToWordsGoA lightweight Go library that provides a simple function to convert numeric values into their corresponding word representation in two languages Arabic and English.
Controllable and fast Text-to-Speech for over 7000 languages!
Levenshtein implements the Levenshtein (edit distance and diff) algorithm for golang
SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming: Training a Speech Language Model on One GPU in a Day"
Convert Hebrew between UTF-8 and Tiqwah ASCII representation, also phonetic SAMPA IPA
Collection of pretrained models for the Montreal Forced Aligner
GUI Grounding for Professional High-Resolution Computer Use
An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI
Convert phoneme codes and lexicon formats for English speech synths
A browser-based tool to convert International Phonetic Alpha (IPA) phonetic notation to speech using the meSpeak.js package
Character-level conversion between Hebrew text and Latin transliteration using deep learning - a demonstration of seq2seq training.
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …
PhonoGlyphe is a G2P transformer model meant as a fallback method for the Misaki G2P engine.
Tiny python library with zero dependencies which generates formatted multiline tables in markdown
High quality text-to-speech based on StyleTTS 2.
Quickly rewrite git repository history (filter-branch replacement)