Tokenization & Preprocessing
OpenMOSS/MOSS-Audio-Tokenizer
A 1.6B causal Transformer audio tokenizer with streaming, variable bitrates, and semantic alignment across speech, sound, and music
PythonApache-2.0updated Jun 16, 2026
🏆 #2,604 overall#105 of 148 in Tokenization & Preprocessing
Voine /Bert-VITS2-MNN
A practical on-device BertVITS2 runtime for Android, powered by alibaba-MNN engine. 面向移动端离线语音合成的轻量化 BertVITS2 工程实现，基于阿里 MNN 推理框架。
$ git clone https://github.com/Voine/Bert-VITS2-MNN.gitStars
162
162
Forks
21
21
Language
C++
License
Apache-2.0
Created
Apr 23, 2025
1.4 years old
Last push
Aug 5, 2026
Categories
More in Tokenization & Preprocessing
Tokenization & Preprocessing
theseer/tokenizer
A small library for converting tokenized PHP source code into XML (and potentially other formats)
PHPOtherupdated Feb 3, 2026
Tokenization & Preprocessing
marcelroed/gigatoken
Language model tokenization at GB/s
🧠 Natural Language Processing
RustMITupdated Sep 2, 2026
Tokenization & Preprocessing
andialbrecht/sqlparse
A non-validating SQL parser module for Python
PythonBSD-3-Clauseupdated Aug 13, 2026
Tokenization & Preprocessing
Chevrotain/chevrotain🔥 active
Parser Building Toolkit for JavaScript
TypeScriptApache-2.0updated Sep 24, 2026
Tokenization & Preprocessing
Data from GitHub · snapshot Sep 24, 2026