asr

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust

Voice AI runtime. Local first transcription, speaker diarization, TTS, and voice cloning with an OpenAI compatible API.

A live speech recognition using Facebooks wav2vec 2.0 model.

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.

A lightweight Python package for Automatic Speech Recognition using ONNX models

Striving to create a great Application with full functions of learning languages by ChatGPT, TTS, STT and other awesome AI models, supports talking, speaking assessment, memorizing words with contexts, Listening test, so on.

Проект для распознавания речи на русском языке на основе pykaldi.

Open-source voice typing for Windows — a Wispr Flow / Superwhisper alternative. Press a shortcut, speak, and AI-polished text lands at your cursor. Local models, your own API keys, or a self-hosted backend.

audio.cpp with a full-task WebUI - pure C++ audio-model inference engine powered by ggml. TTS, ASR/STT, VAD, voice conversion, speaker diarization, music generation. No Python dependency.

Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖

End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)

Your faithful, impartial partner for audio evaluation — know yourself, know your rivals. 真实评测，知己知彼。A unified benchmark framework for ASR/TTS/Audio Codec/audio LLM evaluation

Ultra fast and portable Parakeet implementation for on-device inference in C++ using Axiom with MPS+Unified Memory

Snap any video URL or audio file into plaintext. No GPU. No cloud. One command.

Working online speech recognition based on RNN Transducer. ( Trained model release available in release )

T-one is a high-performance streaming ASR pipeline for Russian, specialized for the telephony domain.

Official JavaScript SDK for Deepgram.

Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021) and WavLM (2022) pretrained on a corpus of English speech that we will use in various ways to perform phoneme recognition for different languages with a network trained with Connectionist Temporal Classification (CTC) algorithm.

System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.