A fully local audio transcription, diarization and summarizing application written in Python. Converts therapy sessions into transcripts and summarizes key topics. Currently set up to process Dutch audio files, but can be modified to fit other languages. Model downloads NOT included.
🎙️A voice-assistant project that combines a Python backend with a web-based interface built using JavaScript, HTML, and CSS. It’s designed to handle voice-driven interactions while providing a responsive UI for controlling and visualizing assistant features.
This repository contains locally performed tests for several open source models and the results. It also contains verified snippets on how to prepare some types of data for training and/or fine-tuning, as well as validating local setups. It contains a fine tuning example of LLM for generating travel itineraries (using DPO). More to be added.
Streamlit application for transcription and translation using OpenAI Whisper on Apple Silicon with MLX.
To associate your repository with the whisper-large-v3-turbo topic, visit your repo's landing page and select "manage topics."