Lists (16)
Stars
A library to manipulate font files from Python.
[ICLR 2025] Binary Spherical Quantization + [CVPR 2026] Leech Spherical Quantization
[ICLR 2026] Official implementation of Toward Complex-Valued Neural Networks for Waveform Generation
The repo provides information about KeSpeech dataset.
Large, modern dataset for speech recognition
A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation
Official repository for the WenetSpeech-Chuan dataset.
A Large-scale Wu Dialect Speech Corpus with Multi-dimensional Annotations
List of papers studying machine learning through the lens of category theory
Helper for managing arXiv papers in Zotero
OLaPh (Optimal Language Phonemizer) is a multilingual phonemization framework that converts text into phonemes surpassing the quality of comparable frameworks.
Comparison of Python audio resampling implementations
Official code for Interspeech 2023 paper "Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering"
The Smallest English TTS Model with only 1M parameters
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
A library to analyze PyTorch traces.
Kanade is a single-layer disentangled speech tokenizer that extracts compact tokens suitable for both generative and discriminative modeling.
Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate
Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
High-Quality Voice Cloning TTS for 600+ Languages
RWKV-LM-V7(https://github.com/BlinkDL/RWKV-LM) Under Lightning Framework
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。
原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复