speech-translation

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Build voice agents with open-source models

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.

End-to-End Speech Processing Toolkit

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

Real-time two-way speech translation for bilingual meetings — auto-detects the spoken language and translates both directions, cloud or fully offline on-device. Desktop (Windows · macOS · Linux) + browser extension (Chrome · Edge) for Zoom, Meet, Teams & any app.

The dataset of Speech Recognition

Cross-platform speech toolset, used from the command-line or as a Node.js library. Includes a variety of engines for speech synthesis, speech recognition, forced alignment, speech translation, voice isolation, language detection and more.

MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction models along with training and inference code, covering but not limited to end-to-end speech interaction, end-to-end speech translation and speech recognition.

This repository outlines the procedures and general information for the Speech Translator project.

Repository containing the open source code of works published at the FBK MT unit.

Real-time on-device speech translation for macOS. Silero VAD + Qwen3-ASR-1.7B + Qwen3.5 (MLX) on Apple Silicon. No cloud, no API keys, no telemetry.

Real-time voice translator for video calls. Speak your language on Google Meet, Zoom, or any call app — the other person hears translated speech instantly. Speech-to-speech translation with Deepgram STT, Groq LLM, and Piper TTS. 29 languages, local neural TTS, call history with AI summaries. Elixir + Rust + Python. macOS.

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

🚀 Framework for seamless fine-tuning of Whisper model on a multi-lingual dataset and deployment to prod.

A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.

Code for ACL 2022 main conference paper "STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation".

StreamUni is a framework that efficiently enables unified Large Speech-Language Models to accomplish streaming speech translation in a cohesive manner.

PyTorch toolkit for streaming speech recognition, speech translation and simultaneous translation based on fairseq.

A blazing-fast, offline push-to-talk voice assistant. Features real-time Whisper.net transcription, auto-typing under caret, smart VAD, and seamless translation to English.