Pinned Repositories
A-real-time-time-domain-speech-enhancement-model
AEC-ANS-AGC
AEC/ANS/AGC from webrtc
asteroid
The PyTorch-based audio source separation toolkit for researchers || Current highlight : we got our WHAMR results check it out here !
AudioBSS
Blind source seperation of audio records
awesome-vad
A curated list of awesome voice activity detection
Chinese-Synonyms
Chinese Synonyms 中文同义词查询工具包
chinese_keybert
A minimal chinese keywords extraction with BERT
essentia
C++ library for audio and music analysis, description and synthesis, including Python bindings
Realtime_AudioDenoise_EchoCancellation
Speech-Separation-Paper-Tutorial
A must-read paper for speech separation based on neural networks
ROAD2018's Repositories
ROAD2018/AQUA-Tk
AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)
ROAD2018/aichat
All-in-one AI-Powered CLI Chat & Copilot that integrates 20+ AI platforms, including OpenAI, Azure-OpenAI, Gemini, Claude, Mistral, Cohere, VertexAI, Bedrock, Ollama, Ernie, Qianwen, Deepseek...
ROAD2018/icefall
ROAD2018/sherpa-onnx
Speech-to-text, text-to-speech, and speaker recongition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift
ROAD2018/ChatRWKV
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
ROAD2018/RWKV-Runner
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.
ROAD2018/Top2Vec
Top2Vec learns jointly embedded topic, document and word vectors.
ROAD2018/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
ROAD2018/lxcfs
FUSE filesystem for LXC
ROAD2018/Detecting-Deepfake-Using-Audio-and-Visual-Emotion-Synchronization
Deepfake detection using audio and facial emotion synchronization
ROAD2018/open-unmix-pytorch
Open-Unmix - Music Source Separation for PyTorch
ROAD2018/Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
ROAD2018/libwebsockets
canonical libwebsockets.org networking library
ROAD2018/ZLMediaKit
WebRTC/RTSP/RTMP/HTTP/HLS/HTTP-FLV/WebSocket-FLV/HTTP-TS/HTTP-fMP4/WebSocket-TS/WebSocket-fMP4/GB28181/SRT server and client framework based on C++11
ROAD2018/dejavu
Audio fingerprinting and recognition in Python
ROAD2018/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
ROAD2018/ChatLM-mini-Chinese
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。
ROAD2018/music_source_separation
ROAD2018/StableTTS
Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3
ROAD2018/websockets
Library for building WebSocket servers and clients in Python
ROAD2018/GPT-SoVITS-Server
【脱离复杂的环境配置和整合包，极简配置推理服务】从GPT-SoVITS项目里面提取出来的，纯粹的推理服务方案。
ROAD2018/sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
ROAD2018/ASR-2Pass
ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).
ROAD2018/cibuildwheel
🎡 Build Python wheels for all the platforms with minimal configuration.
ROAD2018/TextRank4ZH
:deciduous_tree:从中文文本中自动提取关键词和摘要
ROAD2018/kaldifeat
Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API
ROAD2018/YAYI-UIE
雅意信息抽取大模型：在百万级人工构造的高质量信息抽取数据上进行指令微调，由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)
ROAD2018/FunClip
一款基于FunASR高准确率开源语音识别模型的智能视频剪辑工具 / A video clipping tool based on FunASR open source model and Gradio.
ROAD2018/pke_zh
pke_zh, python keyphrase extraction for chinese(zh). 中文关键词或关键句提取工具，实现了KeyBert、PositionRank、TopicRank、TextRank等算法，开箱即用。
ROAD2018/Sensitive-lexicon
敏感词库旨在建立一个词汇集，用于识别和过滤文本内容中的不当或不适宜的语言，以保护用户免受有害信息的影响并维持沟通环境的健康。