Is This The Fastest ASR?

Sam Witteveen · Advanced ·🧠 Large Language Models ·3h ago
In this video, I dive into IBM's newly released Granite Speech 4.1 models and explore what makes them interesting — particularly the three 2B variants they've dropped and how each one makes a different trade-off between accuracy, richness, and throughput that you'll actually care about for real applications. 🔗 Links: IBM Research Blog → https://research.ibm.com/blog/granite-4-1-ai-foundation-models Twitter: https://x.com/Sam_Witteveen 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: https://drp.li/dIMes 👨‍💻Github: https://github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro 00:20 IBM Granite Collection 00:27 Granite Docling 00:46 Granite Speech 4.1 01:16 Granite 4.1 Blog 01:38 Granite Speech 4.1 2B 04:02 Granite Speech 4.1 2B Plus 06:15 Granite Speech 4.1 2B NAR 07:30 NLE: Non-autoregressive LLM-based ASR by Transcript Editing Paper 07:45 Architecture 09:45 Code Time 12:00 Granite Speech Model Github #DellProPrecision #DellProMax #Delltech #localai #NVIDIA
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

⚡
LLM Cost Calculator
Estimate monthly costs for LLM models like Claude, GPT, and Llama using a free cost calculator tool, and understand the importance of cost estimation in AI model selection
Dev.to · Codehelper
 ⚡
How to Run Claude Code Locally (100% Free & Fully Private)
Run Claude code locally for free and private AI development
Medium · LLM
 ⚡
Stop Blaming Claude Opus 4.7. Your Prompts Were Always Broken — 4.6 Was Just Carrying You.
Learn how to craft effective prompts for LLMs like Claude Opus 4.7 and avoid blaming the model for poor results
Medium · LLM
 ⚡
AI Isn’t “Inspired” by Human Writing. It Is Built on Unpaid Intellectual Labor
AI models are built on unpaid intellectual labor, erasing attribution and recombining human knowledge, highlighting ethical concerns in AI development
Dev.to AI

Chapters (12)

Intro
0:20 IBM Granite Collection
0:27 Granite Docling
0:46 Granite Speech 4.1
1:16 Granite 4.1 Blog
1:38 Granite Speech 4.1 2B
4:02 Granite Speech 4.1 2B Plus
6:15 Granite Speech 4.1 2B NAR
7:30 NLE: Non-autoregressive LLM-based ASR by Transcript Editing Paper
7:45 Architecture
9:45 Code Time
12:00 Granite Speech Model Github
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →