#asr Repositories
101 repositories total
First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come back to MEGA-ASR, after the rest fail in the wild. โญ**
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
VocoType is a privacy-secure voice input tool that runs on the local client side. With a shortcut key, it converts voice to text in real-time and automatically inputs it into the current application. It supports functions such as voice-to-text MCP, AI-optimized text, custom replacement dictionary, audio/video transcription, making voice input more efficient and secure.
BYOK voice recording companion with ASR transcription, speaker diarization, AI summaries, and support for local ASR endpoints.
๐ฅ๐ฅ๐ฅFree offline AI algorithm toolbox for Java, supporting face recognition, liveness detection, expression recognition, object detection, instance segmentation, pedestrian detection, OCR text recognition, license plate recognition, table recognition, ASR+TTS, machine translation, and other functions, usable via Maven reference. Supports PyTorch, Tensorflow, and has integrated mainstream models such as Mtcnn, InsightFace, SeetaFace6, YOLOv8~v12, PaddleOCR(PPOCRv5), Whisper, etc.
Real-time audio translation, captures system audio + mic, runs ASR (Whisper/SenseVoice), translates via LLM API with streaming display. Perfect for VTubers, livestreamers, and watching foreign content.
Voice input for macOS with local models: transcribe, translate, and rewrite in any app. The successor to Voxt.
This project provides an API with user level access support to transcribe speech to text using a finetuned and processed Whisper ASR model.
Omni SenseVoice: High-Speed Speech Recognition with words timestamps ๐ฃ๏ธ๐ฏ
An LLM ASR voice input method keyboard application for the Android platform based on Kotlin
A user-friendly toolkit for voice recognition/transcription/conversion etc. | A simple and easy-to-use voice toolkit
End-to-end Chinese speech recognition based on PaddlePaddle, from entry to practice, super simple introductory cases, super practical enterprise projects. Supports the currently most popular DeepSpeech2, Conformer, Squeezeformer models.
GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters
AI VTuber with LLM, ASR, TTS, OCR, CV and more technologies to live stream or play Minecraft with you.
Voxtral ASR & TTS running natively and in the browser. A Rust implementation of Mistral's Voxtral mini realtime ASR / TTS using the Burn ML framework
๐ฆ Quick conversion between ยซChinese numeralsยป and ยซArabic numeralsยป ~ (Latest feature: fractions, dates, temperatures, etc.๏ผ
Speech recognition implemented based on PaddlePaddle, Chinese speech recognition. The project is complete with good recognition performance. Supports training and prediction on Windows and Linux, supports prediction on Nvidia Jetson development board.
A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.
Running speech to text model (whisper.cpp) in Unity3d on your local machine.
A Pytorch-based framework for streaming and non-streaming automatic speech recognition, compatible with both online and offline recognition. It currently supports Conformer, Squeezeformer, and DeepSpeech2 models, along with various data augmentation methods.
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
Real Time Speech Transcription with FastRTC โก๏ธand Local Whisper ๐ค
Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android
INTERSPEECH 2023-2024 Papers: A complete collection of influential and exciting research papers from the INTERSPEECH 2023-24 conference. Explore the latest advances in speech and language processing. Code included. Star the repository to support the advancement of speech technology!
AI Video Narration Agent Skill Pack: automatically cuts scenes, watches the footage to write narration, adds voice-over and mixes audio to produce the final video, and exports drafts for Jianying/CapCutโno GPU required | Agent skills for narrated video recaps & CapCut drafts
Amo's Subtitle Workbench: Moy's ASR Subtitle Transcription Workflow (MAW for short)
๐ฃ Commercial-grade open-source automatic speech recognition library, out-of-the-box, cross-platform supported, Chinese-English mixed recognition. A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide a set of easier APIs to call ASR models.
Scene-aware storyboard for DeepSeek Harness: 9โ16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.
SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.
Transcribe any video URL or audio file into plaintext. No GPU. No cloud. One command.
An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine
A speech recognition library running in the browser thanks to a WebAssembly build of Vosk
ICASSP 2023-2024 Papers: A complete collection of influential and exciting research papers from the ICASSP 2023-24 conferences. Explore the latest advancements in acoustics, speech and signal processing. Code included. Star the repository to support the advancement of audio and signal processing!
Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription.