---
title: "Reconstructed Slides: Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning  — Merve Noyan, Hugging Face"
category: "slides"
video_id: "OV56RddyFuU"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning  — Merve Noyan, Hugging Face

## Source Video
[Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning  — Merve Noyan, Hugging Face](https://www.youtube.com/watch?v=OV56RddyFuU)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/OV56RddyFuU/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.79`
![[assets/reconstructed-slides/OV56RddyFuU/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.85`
![[assets/reconstructed-slides/OV56RddyFuU/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `169.88`
![[assets/reconstructed-slides/OV56RddyFuU/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.36`
![[assets/reconstructed-slides/OV56RddyFuU/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `173.99`
![[assets/reconstructed-slides/OV56RddyFuU/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `168.22`
![[assets/reconstructed-slides/OV56RddyFuU/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.58`
![[assets/reconstructed-slides/OV56RddyFuU/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `171.18`
![[assets/reconstructed-slides/OV56RddyFuU/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `171.7`
![[assets/reconstructed-slides/OV56RddyFuU/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `171.71`
![[assets/reconstructed-slides/OV56RddyFuU/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.36`
![[assets/reconstructed-slides/OV56RddyFuU/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.44`
![[assets/reconstructed-slides/OV56RddyFuU/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `169.06`
![[assets/reconstructed-slides/OV56RddyFuU/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.32`
![[assets/reconstructed-slides/OV56RddyFuU/slide-015.jpg]]

- Source frame: `slide-015.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `171.73`
![[assets/reconstructed-slides/OV56RddyFuU/slide-016.jpg]]

- Source frame: `slide-016.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `169.51`
![[assets/reconstructed-slides/OV56RddyFuU/slide-017.jpg]]

- Source frame: `slide-017.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.79`
![[assets/reconstructed-slides/OV56RddyFuU/slide-018.jpg]]

- Source frame: `slide-018.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `172.38`
![[assets/reconstructed-slides/OV56RddyFuU/slide-019.jpg]]

- Source frame: `slide-019.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.2`
![[assets/reconstructed-slides/OV56RddyFuU/slide-020.jpg]]

- Source frame: `slide-020.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.15`
![[assets/reconstructed-slides/OV56RddyFuU/slide-021.jpg]]

- Source frame: `slide-021.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.56`
![[assets/reconstructed-slides/OV56RddyFuU/slide-022.jpg]]

- Source frame: `slide-022.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.55`
![[assets/reconstructed-slides/OV56RddyFuU/slide-023.jpg]]

- Source frame: `slide-023.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.57`
![[assets/reconstructed-slides/OV56RddyFuU/slide-024.jpg]]

- Source frame: `slide-024.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.5`
## Dense Scene-Detected Slide Candidates
- [[youtube-OV56RddyFuU-dense-slides]]