OZI - Subtitles Generator with AI

Jocimar Lopes — Wed, 06 Aug 2025 01:34:43 +0000

🎬 It all started with a simple wish: watching The Osbournes with subtitles in Portuguese. 😂

Then I thought… “Why not build my own solution?”

I developed a Python application that automatically generates subtitles for MP4 videos. Just pick a video, choose the subtitle language (EN, PT, ES, FR), and click “Generate Now!” — that’s it.

That's the result:

This project is more than just a personal solution — it’s also a way to showcase my skills in Python, automation, and media processing.

The source code is available on GitHub, along with a complete step-by-step guide to get it up and running:

🔗 Source Code: https://github.com/jocimarlopes/ozi-subtitles-generator

Running on Windows and MacOS:

🔧 Technologies used:
• Python
• MoviePy
• Whisper AI
• PySide6

🔧 Next steps: I’m currently working on slang normalization to improve subtitle quality in Brazilian Portuguese. That feature should be ready soon.

If you like the project, feedback is more than welcome!

Python #OpenSource #DevLife #SideProjects #AutoSubtitles #AI #MachineLearning

Flask API com DeepSeek-R1 via Ollama with Python

Jocimar Lopes — Tue, 13 May 2025 14:43:39 +0000

🧠 Flask API with DeepSeek-R1 via Ollama

This is an API developed with Flask in Python, connecting to the LLM model DeepSeek-R1 using the Ollama platform.

It allows to perform inferences with LLMs in a simple, efficient and local way with a basic UI and response stream return.

⚙️ Prerequisites

Before running the project, make sure you have the following items installed:

Python 3.8+
Ollama
deepseek-r1 downloaded from Ollama

🚀 Installation

Clone the repository

git clone https://github.com/jocimarlopes/ollama-llm-deepseek-server.git
cd ollama-llm-deepseek-server

Install the dependencies

pip install -r requirements.txt

Install and start Ollama If you don't already have Ollama:

# On Linux via curl
curl -fsSL https://ollama.com/install.sh | sh

Download the DeepSeek-R1 model If you don't have Ollama yet:

ollama pull deepseek-r1:latest

🧪 Running the API

Just run the app.py script:

python app.py

📁 Basic structure

Just run the app.py script:

├── app.py
├── requirements.txt
└── README.md

👤 Credits

Project developed by Jocimar Lopes.
Feel free to contribute or use in your own projects.

📄 License

This project is licensed under the terms of the MIT License.

DEV Community: Jocimar Lopes