zhenye234/xcodec🔥 active
AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
A 1.6B causal Transformer audio tokenizer with streaming, variable bitrates, and semantic alignment across speech, sound, and music
$ git clone https://github.com/OpenMOSS/MOSS-Audio-Tokenizer.gitAAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
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。
Kanade is a single-layer disentangled speech tokenizer that extracts compact tokens suitable for both generative and discriminative modeling.
▲ +2 ★ this week
A small library for converting tokenized PHP source code into XML (and potentially other formats)
▲ +2 ★ this week
Language model tokenization at GB/s
A non-validating SQL parser module for Python
Data from GitHub · snapshot Nov 16, 2026