HunyuanVideo-1.5: A leading lightweight video generation model

A small speech recognizer

A high-throughput and memory-efficient inference and serving engine for LLMs

A list of publically available audio data that anyone can download for ASR or other speech activities

Build resilient language agents as graphs.

Custom decoders for Kaldi

ASR online decoding using Kaldi NNet3 GrammarFST

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Semantic Voice Activity Detection adds an lightweight LLM prediction model to continuously evaluate whether a user has really finished speaking.

A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

Official PyTorch implementation of BigVGAN (ICLR 2023)

This is the official repo for the paper "LongCat-Flash-Omni Technical Report"

Official electron build of draw.io

Spark-TTS Inference Code

Spark-TTS Inference Code

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。

一个面向中文文本纠错任务的综合平台，集学术研究、模型训练、模型评测和推理部署于一体，覆盖拼写纠错与语法纠错两个核心方向。

中文文本纠错相关的论文、比赛和工具。

The Swift Programming Language

Code for Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition

LLM-based ASR recipe with Zipformer encoder and Qwen LLM

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…

结巴中文分词

百度NLP：分词，词性标注，命名实体识别，词重要性