PyData Cluj-Napoca: Meetup #22

Are you ready for a new geeky evening?

🌟 Hello PyData Community! 🌟

We had an incredible turnout last month, and we're excited to keep the momentum going with our October meetup! Whether you joined us in September or missed out, this is your chance to dive back into the world of data with fresh talks and great networking opportunities.

Our October session will feature more in-depth presentations, hands-on learning, and some new faces sharing their expertise. It’s the perfect opportunity to deepen your skills, discover innovative solutions, and connect with like-minded data professionals.

Join us for a social and informative evening! (+🍕🍔🌯🌮)
----------------------------------------------------------------------------------------------------

"Type or Dare: Navigating Python’s Typing Ecosystem" By Bogdan Bustan

Python's journey from a purely dynamic language to one that embraces optional static typing is a fascinating evolution in programming language design. This presentation will explore how the introduction of type hints in Python 3.5, through PEP 484, has transformed the language's ecosystem and paved the way for safer, more robust code.

The impact of type hints on the broader Python ecosystem is evident in the emergence of typing-powered frameworks. We'll take a closer look at how Pydantic and FastAPI leverage type annotations to provide powerful data validation and API development capabilities. These frameworks demonstrate the practical benefits of a well-typed codebase in real-world applications.

Python's type system hasn't evolved in isolation. We'll explore how concepts from statically-typed languages, particularly Rust, have influenced Python's typing ecosystem.

By the end of this presentation, you'll have a comprehensive understanding of Python's typing ecosystem, from its foundations to its cutting-edge developments. Whether you're working in data science, web development, or any other Python domain, you'll be equipped to leverage type hints effectively, writing safer, more maintainable code in an ever-evolving language landscape.

----------------------------------------------------------------------------------------------------

⚡ Lightning Talk ⚡

"Skip the line. Using GenAI to analyze your data" By Florin Pavel

If you have data that requires swift analysis or querying, GenAI offers a convenient solution. By configuring GenAI to utilize Pandas behind the scenes, you can efficiently analyze your data, even without a deep understanding of Python. We will then evaluate the quality of the responses through interactive questioning. To illustrate this process, a short demonstration using Python and Langchain will be provided.

----------------------------------------------------------------------------------------------------

"Off-the-shelf HuggingFace models for audio deepfake detection" By Adriana Stan

In this tutorial, we will explore how to leverage off-the-shelf HuggingFace models for detecting audio deepfakes, focusing on state-of-the-art models like wav2vec 2.0 and WavLM. Audio deepfakes, generated by advanced voice cloning technologies, have become a significant concern due to their potential for misuse in areas like misinformation, fraud, and privacy breaches. Tools such as ElevenLabs and Respeecher now enable highly realistic voice replication, making detection technologies more crucial than ever. The tutorial will guide participants through setting up and using pre-trained models for identifying deepfake audio. Both models are built on transformer architectures and have shown strong performance in speech-related tasks, making them suitable candidates for detecting subtle anomalies in synthetic voices.

We will start by introducing the fundamentals of deepfake audio and discuss current trends in voice cloning technologies, highlighting the rise of commercial tools that allow easy generation of cloned voices. The hands-on session will focus on practical implementations. By the end of the tutorial, participants will have a clear understanding of how to utilise these pre-trained models from HuggingFace’s library, extract their representations on labelled deepfake datasets, and evaluate their effectiveness in detecting manipulated audio. Through this process, we aim to bridge the gap between cutting-edge speech generation technologies and the emerging need for highly-accurate deepfake detection systems.

----------------------------------------------------------------------------------------------------
NumFOCUS Code of Conduct
https://numfocus.org/code-of-conduct