Category/Tag: Artificial Intelligence

Inside the Qwen3-TTS Engine Code (Qwen3-TTS, Part 2)

Inside the Qwen3-TTS Engine Code (Qwen3-TTS, Part 2)

What does it actually take to plug a brand-new AI voice engine into an existing codebase without breaking everything else? This post pulls back the curtain on the code behind Book2Audio's Qwen3-TTS integration — from the two-method abstraction that makes any TTS engine swappable, to the GPU memory tricks that squeeze a 1.7B model onto a consumer laptop.


Refactoring the Book2Audio Parsers

Refactoring the Book2Audio Parsers

The unglamorous work of software is making things consistent — and this update to Book2Audio is exactly that. Two parsers that did the same job differently have been brought into alignment, sharing a single text-cleaning pipeline and a unified paragraph accumulation strategy. It's the kind of refactor that doesn't change what the tool does today, but makes possible something much more interesting tomorrow: an LLM-based cleaning step that can fix the OCR errors, broken page splits, and stray footnotes that rule-based cleaning can never quite catch.


What Exactly Is an Inductive Bias?

What Exactly Is an Inductive Bias?

Every learning algorithm is making a bet. It can't prove its predictions from the data alone — it's sneaking in assumptions, whether it admits them or not. Name those assumptions precisely enough, and something surprising emerges: there's no such thing as induction. It's deduction in disguise. This post unpacks what that means, why stronger assumptions lead to better generalization and more spectacular failures, and what it reveals about neural networks that most people never think to ask.


Adding EPUB Support to Book2Audio

Adding EPUB Support to Book2Audio

Book2Audio started as a PDF converter — but the best books often come as EPUBs. This post walks through how we added EPUB support, what it took to strip a RAG-focused parser down to something clean enough for audio, and the small details that turn out to matter when you're reading a book aloud: chapter titles that actually get spoken, footnote markers that don't interrupt the flow, and a debug mode that shows you exactly what the parser heard before you commit to a three-hour conversion run.


Implementing Qwen3-TTS in My PDF-to-Audiobook Pipeline (Qwen3-TTS, Part 1)

Implementing Qwen3-TTS in My PDF-to-Audiobook Pipeline (Qwen3-TTS, Part 1)

What if you could turn any PDF into an audiobook and fine-tune the narrator's voice with nothing but a plain English instruction? Alibaba just open-sourced Qwen3-TTS, and it's worth paying attention to — nine built-in speakers, natural language style control, and weights you can run on a laptop GPU. But does it actually sound good enough to listen to for hours? The answer might surprise you.


Machine Learning 101: The Key Concepts Behind Every Learning Algorithm

Machine Learning 101: The Key Concepts Behind Every Learning Algorithm

Machine learning textbooks have their own vocabulary. But behind the jargon lies a process that would be deeply familiar to Karl Popper: conjecture and refutation. This post is a short reference guide


Book2Audio: Reviving My PDF-to-Audiobook Project (and Fighting Dependency Hell Along the Way)

Book2Audio: Reviving My PDF-to-Audiobook Project (and Fighting Dependency Hell Along the Way)

Converting PDFs to audiobooks sounds simple. It is not. Memory crashes, dependency hell, and software updates that break more than they fix — but the result is a working open-source pipeline that turns any PDF into audio you'd actually want to listen to. And the best parts are still coming.


Induction is a Myth: The Futility of Unbiased Learning

Induction is a Myth: The Futility of Unbiased Learning

A philosopher and a computer scientist walk into the same conclusion from opposite directions: you can't learn anything from data alone. Popper said induction was a myth. Mitchell proved it mathematically. And the punchline? Every machine learning algorithm that does generalize is secretly running deduction in disguise — the "induction" was never really there.


Adventures in LangChain's "Quick Start Tutorial" (Using Ollama)

Adventures in LangChain's "Quick Start Tutorial" (Using Ollama)

LangChain is a great framework for turning chatbots into functional tools. Today, we'll be having a look at LangChain's own Quick Start Tutorial and how we were able to get it to work with Ollama for a free.


Weekend Warrior Project: AI Patent Checking

Weekend Warrior Project: AI Patent Checking

Every day we hear about how AI is constantly improving in its intelligence and its capabilities, but many still wonder how AI can actually help improve their daily workloads. In today's AI tutorial, we'll be showcasing a real-world example of how we were able to build and use an AI agent to help us sift through the millions of patents that exist in the USPTO records; turning weeks of work into mere hours (including the time it took to build the AI agent).