OpenAI Whisper
Speech-to-text transcription model
Episodes
-
#6160: Where Do Tiny Speech Rules Live? A Ladder From Regex to LoRAA regex notebook, a WFST grammar, or a fine-tune? Where do tiny speech-rewrite rules actually belong in a 600M-parameter model? -
#3365: Does Learning an Enemy's Language Change You?How deep language learning can erode ideological commitment — and where organizations build firewalls against it. -
#2773: Beyond Static Fallbacks: Agentic Error Handling in AI PipelinesFrom try-except blocks to planning agents that route around failures intelligently. -
#2543: Why Base64 Adds 33% Overhead (And Why You Still Need It)Base64 isn’t compression — it’s a safe transport encoding. Here’s how it works with audio APIs and where its limits are. -
#1540: Why Gnome 50 is Breaking Your Voice-to-Text ToolsExplore the engineering battle to bring low-latency AI voice input to Linux while navigating the strict security of Wayland and GNOME 50. -
#322: Why You Can't Stop Thinking About Work After 5 PMStruggle to shut down your brain at night? Discover how a simple voice note can bridge the gap between today’s work and tomorrow’s flow. -
#22: The Input Bottleneck: Why Your Mic Matters for AIUncover the secrets to perfect AI dictation! Corn and Herman explore the ultimate speech-to-text hardware.