Published inArtificial Intelligence in Plain EnglishWhisper Word-Level Timestamps: Overcoming Challenges with whisper-timestampedAutomatic speech recognition (ASR) has made significant strides in recent years, with OpenAI’s Whisper model leading the way in…Feb 1250Feb 1250
Understanding Audio Diarization: Analyzing Channel Activity in Audio FilesAudio diarization, the process of identifying “who spoke when” in an audio recording, plays a critical role in many real-world applications…Jan 851Jan 851
Guide to Data Storage Options in Pandas: Benefits and DrawbacksWhen working with data in Python, Pandas is the go-to library for data manipulation and analysis. However, storing and persisting data…Jan 8Jan 8
Discover the Speed Boost: FireDucks vs PolarsIn the realm of data analysis, efficient data manipulation is crucial. While pandas has been the go-to library for Python enthusiasts…Jan 51Jan 51
NotebookLM: Redefining Knowledge Management with AI-Driven InsightsNavigating the ever-growing volume of digital information is an ongoing challenge. Google’s NotebookLM is here to change that. Powered by…Dec 12, 202450Dec 12, 202450
Optimizing Whisper ASR Model — Parameters for Enhanced PerformanceWhen working with Whisper for automatic speech recognition (ASR), tuning the model parameters significantly affects the accuracy…Oct 25, 202450Oct 25, 202450
Published inGenerative AIAdvanced RAG using Document Summarisation : Two-Step Retrieval with ChromaDBRetrieval-Augmented Generation (RAG) is a critical technique for building applications that leverage large language models (LLMs) by…Oct 21, 202450Oct 21, 202450
Published inGenerative AIAutomate Speech-to-Text with Python, Whisper and AWS S3An Overview of the Python AWS S3 Data Pipeline: Boosting Efficiency and Automating Speech-to-Text TasksOct 11, 202452Oct 11, 202452
Published inGenerative AIWhy ChatGPT-4 with Canvas is the Ultimate Tool for Coding EfficiencyImagine working on a coding problem and having a helper that not only understands the code but actively collaborates with you, making the…Oct 6, 202451Oct 6, 202451
From Temperature to Top-p: Tuning Large Language Model Parameters for Better ResultsLarge Language Models (LLMs) are advanced machine learning models designed to understand and generate human language. They are based on the…Oct 3, 2024Oct 3, 2024
Introduction to Unsupervised Machine Learning: Clustering Techniques1. Introduction to Unsupervised Machine LearningSep 24, 2024Sep 24, 2024
Beginner’s Guide to Fast Audio Transcription with Whisper on EC2 GPU InstancesIntroduction:Sep 14, 20241Sep 14, 20241
Published inGenerative AIAdvanced File Processing Techniques for OCR with Python: Converting PDFs, Word Docs, and More for…Created using CHATGPT 4OSep 3, 2024Sep 3, 2024
Published inPython in Plain EnglishEasy Python Logging Using Decorators1. Introduction to Python LoggingSep 2, 2024Sep 2, 2024
Published inGoPenAIUsing Large Language Models for Intent Classification ProjectsWhats Intent Classification?Aug 26, 2024Aug 26, 2024
Automated Python Code Documentation with LLMs (GPT-4)Why Bother with Documentation? (And Why It’s Such a Pain)Aug 22, 2024Aug 22, 2024
Published inArtificial Intelligence in Plain EnglishUnderstanding GPU Requirements for LLM Fine-TuningAug 3, 2024Aug 3, 2024
Mastering Aperture in Photography: A Simple GuideUnderstanding aperture is crucial for any photographer looking to take control of their images. In this post, we’ll break down what…Jul 26, 2024Jul 26, 2024
Published inGenerative AINext-Gen OCR with Vision LLMs : A Guide to Using Phi-3, Claude, and GPT-4OIntroduction: Revolutionising OCR with Vision LLMsJul 26, 20242Jul 26, 20242