streaming-asr

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

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 Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

On-device VAD / streaming STT / TTS / diarization in C++17 (ONNX + LiteRT) with a voice-agent pipeline. Linux, Windows, Android.

Fast, privacy-first voice typing with streaming transcription and BYOK. 快速、隐私优先的流式语音输入工具，支持自带 API Key。

Streaming on-device speech recognition for Android — NEON-accelerated FastConformer (32M params), cache-aware streaming with 80 ms look-ahead, no cloud. Powered by the VoxRT runtime.

Offline Vietnamese voice AI assistant built on Nemotron-3.5 ASR. 'Nemo ơi' wake word + local skills + Piper TTS. Same pipeline does real-time translation.

Streaming on-device speech recognition for iOS — NEON-accelerated, encrypted FastConformer (32M params), RTF 0.08–0.10 on iPhone 13 Pro Max. Built on the VoxRT custom Rust inference runtime. SwiftPM distribution.

Pre-compiled ASR model weights for the VoxRT on-device runtime. Encrypted .vxrt v2 format. streaming-medium-pc: FastConformer 32M, CTC + RNN-T, CC-BY-4.0 (NVIDIA NeMo).

On-device streaming ASR (speech-to-text) for Linux x86_64 + aarch64 — one hardened .so behind Python (PyPI), Node.js (npm), Go (go get), C/C++ (tarball + CMake). AVX2 on servers, NEON on edge. RNN-T + CTC, RTF 0.06–0.08 on x86_64. Same runtime as voxrt-asr-{android,ios}.

A 1300-hour English speech and text corpus of parliamentary debates for streaming ASR training and benchmarking, speech data filtering and speech data verbatimization.

Faster-Whisper Transcription Server & API is a production-ready speech-to-text micro-service stack that wraps faster-whisper with a streaming FastAPI server, a Celery/Redis background queue, and optional Docker deployment—delivering real-time or batch audio transcription with minimal latency and simple web-hook integration.

OpenAI-compatible proxy bridging Doubao/Volcengine ASR 2.0 (Seed-ASR) WebSocket protocol to /v1/audio/transcriptions; works with Spokenly and OpenAI-compatible clients. OpenAI 兼容代理：将豆包/火山引擎 ASR 2.0（Seed-ASR）WebSocket 协议桥接到 /v1/audio/transcriptions，适用于 Spokenly 与其他 OpenAI 兼容客户端。

Production-ready REST API for Russian speech recognition using T-one model. FastAPI-based service with offline and streaming transcription support.

Lightweight Windows voice input tool with offline streaming ASR, hotwords, and AI text correction

PhD Thesis: "Automatic speech recognition and machine translation with deep neural networks for open educational resources, parliamentary contents and broadcast media" (2024)

SwiftPM streaming ASR runtime for NVIDIA Nemotron 3.5 on Apple CoreAI

Windows 桌面豆包语音输入工具 — 全局快捷键录音 → 火山引擎流式 ASR → 自动粘贴到光标。原生支持豆包平台热词表 ID。

一个流式ASR语音识别工具

Windows AI voice input / 中文语音输入工具 built with Rust/Tauri 2 — global hotkey, Volcengine streaming ASR, floating preview, auto-paste.