whisper

A small wrapper package around whisper-timestamped. Create force-aligned transcription TextGrids from raw audio!

A high-performance Model Context Protocol (MCP) server providing local speech-to-text transcription using whisper.cpp, optimized for Apple Silicon.

Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telephony, no extra API key.

I'm sorry, Dave. I'm afraid I can't let that spam call through. — Local AI answering service with voice cloning, call recording, and sub-second latency. Runs entirely on your GPU. No cloud. No per-minute billing. Just HAL.

Local voice-to-Obsidian pipeline. Faster Whisper on CPU — no cloud, no API keys. Auto-triggered via systemd (Linux/macOS) or Docker.

Cloud-agnostic Agentic AI & Multi-Modal RAG platform with GraphRAG, intelligent routing, MCP enterprise integrations (Odoo, PostgreSQL), and pluggable LLM providers.

Open Server is an OpenAI API Compatible Server for generating text, images, embeddings, and storing them in vector databases. It also includes a chat functionality.

Finetuning Whisper ASR model for Belarusian language

Push-to-talk voice dictation for macOS. 100% local, free, open source. Apple Silicon MLX. No cloud, no subscription.

📋 Clipboard manager for vibe coders — native macOS menu-bar app. Text & image history, screen capture + annotation, scrolling capture, screen recording → video/GIF, OCR, on-device voice & meeting notes (or OpenAI/Gemini), share links from your own S3 bucket. Free, private, open source.

🤖 A WhatsApp bot to transcribe and summarize audio messages.

Push-to-talk dictation for macOS — Vietnamese-first, English-friendly. Hold a key, speak, text appears in any app. Powered by Kyma API.

Data preparation utility for the finetuning of OpenAI's Whisper model.

Whisper in TensorRT-LLM

An optimized FastAPI server for OpenAI's Whisper whisper-large-v3-turbo model using MLX optimization

Add n-gram and LLM language model support to HF Transformers Whisper models.

Fine-Tune Whisper for Italian ASR with transformers

🧠 Multimodal Retrieval-Augmented Generation that "weaves" together text and images seamlessly. 🪡

Final training script from HuggingFace Whisper Fine tuning event - to get best results on finetuned model.

The project,being part of Kagglex BIPOC Mentorship Program final project, aims to train two separate Hindi ASR models using the Facebook Wav2Vec2 (300M parameters) and OpenAI Whisper-Small models, respectively. The goal is to compare their performance, with a target WER of less than 13%, across various Hindi accents and dialects.