Ofrenda Local: an offline ofrenda builder, and why a grandmother's sayings need one language per phrase
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine What I Built Ofrenda Local takes a voice recording of someone telling a story about a relative who passed away and turns it into an ofrenda card: the foods they cooked, the songs they sang, the places they lived, the exact things they used to say, and a short remembrance written in the speaker's…
Ofrenda Local is an offline ofrenda builder that converts a voice recording of someone telling a story about a deceased family member into a Día de los Muertos ofrenda card. The card includes the person's favorite foods, songs, places, and phrases they used to say, along with a short remembrance written in their voice. All processes, such as transcription, writing, and building the card, occur on the user's laptop without any data leaving the device. The project is part of the DEV Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine.
Key facts:
1. Ofrenda Local takes a voice recording and turns it into an ofrenda card containing foods, songs, places, phrases, and a remembrance.
2. The transcription is done using whisper.cpp, and the writing is done with Gemma 3 4B on llama.cpp.
3. The glue between the transcription and writing is a Python file with no external dependencies.
4. The project focuses on keeping the original speaker's voice and ensuring the model doesn't put words in their mouth.
5. Demo: https://designmaster-solutions.github.io/ofrenda-local/
The project emphasizes the importance of preserving family memories and stories, and it aims to create an offline, self-contained tool to achieve this goal.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
