Real-time speech-to-text translation over WebSocket. Streams Opus or raw PCM audio from client to server for live transcription and optional translation. Supports CLI and Python API.
-
Updated
May 30, 2026 - Python
Real-time speech-to-text translation over WebSocket. Streams Opus or raw PCM audio from client to server for live transcription and optional translation. Supports CLI and Python API.
This is is a fork of the Subtitle Editor Plugin for Peertube. It adds the ability to translate subtitles to a new language using the Subtitle-Translator project which uses OPUS-MT models to translate subtitles files.
Flask-based API that provides a user-friendly interface to summarize text in any language supported by the BART model and then translate it to English.
🌐 Sophisticated Telegram translator bot with automatic language detection, 50+ language pairs, and Helsinki-NLP models. Built with FastAPI, aiogram, and transformers.
High-performance, asynchronous translation service leveraging the Helsinki-NLP OPUS-MT zh-en model optimized via CTranslate2. The solution provides a RESTful API endpoint that accepts Chinese text input and returns English translations with sub-second latency. Development supported by DeepSeek.
Bidirectional Urdu↔English translation service on Helsinki-NLP MarianMT — FastAPI + vanilla-JS web UI with RTL handling, mocked API tests, CPU-runnable.
Spanish literary translation system, fine-tuned using PEFT with LoRA for high accuracy and minimal compute cost. Built with an intuitive, premium-grade web interface with FastAPI, Bootstrap andcustom animations
Translate from English to French using machine translation models. It includes training and evaluating Helsinki-NLP's Opus-MT and Google's T5 models on the WMT14 French-English dataset. The integration allows users to practice literacy in both English and French
WYL ASR 是一个面向会议、访谈、培训、媒体资料和业务录音的语音内容处理平台。系统基于 FunASR 构建,将以下两项能力作为同等重要、相互独立的核心功能: 实时转写:通过 WebSocket 持续接收麦克风或音频设备的实时音频流,边说边显示文字,并可使用 2pass 模式对流式结果进行校正。 上传音视频转文字:通过 REST API 上传已有音频或视频文件,以后台任务方式完成媒体转换、整文件识别、说话人分段、声纹匹配、翻译和结果整理。 两条链路共用会议管理、热词、说话人声纹库、翻译、会议纪要、Word/PDF 导出和资料归档能力,但使用不同的传输协议、任务状态、模型实例和处理参数。
English-to-Turkish book translator with OCR, archive source lookup, and DOCX QA/proofread workflow.
Transcribe and translate your video locally, directly on your device.
This is an API that uses a fork of the Subtitles-Translator project to translate subtitles from one language to another. It was made to work in pair with our Subtitle Translator Peertube plugin, which is a fork of the Subtitles-Editor plugin for PeerTube.
Instant AI popup translator for macOS — select text, double-press Cmd+C, get a Claude/ChatGPT/offline translation at your cursor
Offline neural machine translation & language detection for DuckDB (Python, Argos)
multi-language translate using UKPLab/EasyNMT
Simple AI translation panel for Lute using FastAPI and Helsinki-NLP OPUS-MT models
Add a description, image, and links to the opus-mt topic page so that developers can more easily learn about it.
To associate your repository with the opus-mt topic, visit your repo's landing page and select "manage topics."