Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

i compared the top open-source OCR solutions and found which one works the best. featuring: > DeepSeek OCR > Datalab Chandra > Qwen3-VL > Dots OCR > Granite Docling also created an app that lets you run all of these OCR models in one place. 100% open-source.

Akshay 🚀

261,984 subscribers

45,427 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

NVIDIA's LocateAnything is a new vision model for grounding and detection. Very performant and accurate! > 10x faster than Qwen3-VL > 138M queries + 785M boxes > GUI, OCR, docs, dense detection > Free & open source

NVIDIA's LocateAnything is a new vision model for grounding and detection. Very performant and accurate! > 10x faster than Qwen3-VL > 138M queries + 785M boxes > GUI, OCR, docs, dense detection > Free & open source

⚡AI Search⚡

120,567 views • 1 month ago

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

Akshay 🚀

251,968 views • 10 months ago

Baidu Inc. just dropped PaddleOCR-VL-1.5, and it’s not just another OCR model. This is a fully open-source OCR model with just 0.9B parameters, built specifically for production-grade document understanding. And the results speak loudly 👇 On OmniDocBench V1.5, the most authoritative global document parsing benchmark, PaddleOCR-VL-1.5 ranks #1 overall, hitting 94.5% overall accuracy, outperforming models like DeepSeek-OCR2. As the first OCR model natively supporting irregular document layout positioning, it perfectly solves OCR pain points in production for complex structured business documents such as financial reports and insurance forms. While a lot of the industry is racing toward bigger models, PaddleOCR is betting on something smarter: small parameters + high performance + open source + real usability. That combination is exactly what scalable document intelligence needs right now. Demo / API → Open source → Model → Curious to see how teams start building on top of this.

Baidu Inc. just dropped PaddleOCR-VL-1.5, and it’s not just another OCR model. This is a fully open-source OCR model with just 0.9B parameters, built specifically for production-grade document understanding. And the results speak loudly 👇 On OmniDocBench V1.5, the most authoritative global document parsing benchmark, PaddleOCR-VL-1.5 ranks #1 overall, hitting 94.5% overall accuracy, outperforming models like DeepSeek-OCR2. As the first OCR model natively supporting irregular document layout positioning, it perfectly solves OCR pain points in production for complex structured business documents such as financial reports and insurance forms. While a lot of the industry is racing toward bigger models, PaddleOCR is betting on something smarter: small parameters + high performance + open source + real usability. That combination is exactly what scalable document intelligence needs right now. Demo / API → Open source → Model → Curious to see how teams start building on top of this.

Bishal Nandi

35,318 views • 4 months ago

$話題の DeepSeek-OCR を動かしてみた。このプロンプトは "<image>\n<|grounding|>Convert the document to markdown. " で画像を Markdown化するもの$

話題の DeepSeek-OCR を動かしてみた。このプロンプトは "<image>\n<|grounding|>Convert the document to markdown. " で画像を Markdown化するもの

null-sensei

44,487 views • 8 months ago

Unlimited-OCR 🔥New OCR from PaddlePaddle It can parse hundreds of pages in a single pass while maintaining stable speed. The key idea is R-SWA (Reference Sliding Window Attention), which keeps KV cache constant during decoding. 🏆 93% on OmniDocBench 📈 +6% over DeepSeek-OCR

Unlimited-OCR 🔥New OCR from PaddlePaddle It can parse hundreds of pages in a single pass while maintaining stable speed. The key idea is R-SWA (Reference Sliding Window Attention), which keeps KV cache constant during decoding. 🏆 93% on OmniDocBench 📈 +6% over DeepSeek-OCR

Adina Yakup

278,576 views • 5 days ago

Launching A2Z Sheet — for Open Source. 🎉 Live at Feats: > for the beginners / who struggle in open source > free > live progress tracking > download the notes > share (if you want) > doc for each module > video for each module

Launching A2Z Sheet — for Open Source. 🎉 Live at Feats: > for the beginners / who struggle in open source > free > live progress tracking > download the notes > share (if you want) > doc for each module > video for each module

Ajeet ( opensox.ai )

31,581 views • 7 months ago

> 2 hours with Claude Code > native macOS app > open source > 🤯🤯🤯

> 2 hours with Claude Code > native macOS app > open source > 🤯🤯🤯

Viktor Seraleev

27,704 views • 1 month ago

launching our open source OCR tool today! try it out with some terrible pdfs and let me know how it goes:

launching our open source OCR tool today! try it out with some terrible pdfs and let me know how it goes:

Tyler Maran

342,666 views • 1 year ago

stop using VLMs blindly ✋🏻 compare different VLM outputs on a huge variety of inputs (from reasoning to OCR!) 🔥 > has support for multiple VLMs: Gemma 3, Qwen2.5VL, Llama4 > recommend us new models or inputs, we'll add 🫡

stop using VLMs blindly ✋🏻 compare different VLM outputs on a huge variety of inputs (from reasoning to OCR!) 🔥 > has support for multiple VLMs: Gemma 3, Qwen2.5VL, Llama4 > recommend us new models or inputs, we'll add 🫡

merve

13,154 views • 1 year ago

I just built my own OCR app powered by Google's Gemma 3. It runs 100% locally on my computer using Ollama and extracts text from images as structured markdown. The code is open-source, and you can find it in the next tweet.

I just built my own OCR app powered by Google's Gemma 3. It runs 100% locally on my computer using Ollama and extracts text from images as structured markdown. The code is open-source, and you can find it in the next tweet.

Akshay 🚀

477,685 views • 1 year ago

I made my own visual novel OCR app that overlays text directly on top of the game. It also has context-aware dictionary results and translations. Also Anki support.

I made my own visual novel OCR app that overlays text directly on top of the game. It also has context-aware dictionary results and translations. Also Anki support.

funorange

224,538 views • 18 days ago

npm install -g cline Not just Cline in the terminal, but the primitive you can build on. > scriptable > open-source > open-model Return to the primitives. (Preview)

npm install -g cline Not just Cline in the terminal, but the primitive you can build on. > scriptable > open-source > open-model Return to the primitives. (Preview)

Cline

49,366 views • 8 months ago

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀

alphaXiv

285,001 views • 8 months ago

> be jesse pollak > unbox dGEN1 phone > supportingbuilders.jpg > realize it works with Base App > start talking to yourself via XMTP > lose your mind about open protocols > mfw crypto is the best industry in the world

> be jesse pollak > unbox dGEN1 phone > supportingbuilders.jpg > realize it works with Base App > start talking to yourself via XMTP > lose your mind about open protocols > mfw crypto is the best industry in the world

Base

107,917 views • 8 months ago

I just made an open-source version of Dhruv Rathee AI startup. > Even with more models :) Link in comments

I just made an open-source version of Dhruv Rathee AI startup. > Even with more models :) Link in comments

Humi

202,636 views • 10 months ago

I am in disbelief... Claude Fable (Mythos) one shot Replit (A Mobile app that builds Web Apps) Prompt was basically: "build an app like Replit, that uses Daytona for sandboxing, and convex for DB" > Builds Apps > Preview App > Open in Browser > Edit app hahaha wow....

I am in disbelief... Claude Fable (Mythos) one shot Replit (A Mobile app that builds Web Apps) Prompt was basically: "build an app like Replit, that uses Daytona for sandboxing, and convex for DB" > Builds Apps > Preview App > Open in Browser > Edit app hahaha wow....

Riley Brown

442,593 views • 17 days ago

wow, total BoM cost $660, folks open-source community >> closed source hyped robots

wow, total BoM cost $660, folks open-source community >> closed source hyped robots

Thomas Wolf

192,471 views • 9 months ago

> checking indicators. > watching the 1s chart. > position opened. > session complete. Agent Trade Kit. Open source. Local-first. Live now.

> checking indicators. > watching the 1s chart. > position opened. > session complete. Agent Trade Kit. Open source. Local-first. Live now.

OKX

33,067 views • 3 months ago

Can Google Gemma DiffusionGemma help fix broken OCR? In theory, denoising tokens in parallel could work better for OCR correction since context is seen upfront? Pointed it at 19th-century newspaper OCR. It corrected better than the autoregressive baseline — at ~8x the speed.

Can Google Gemma DiffusionGemma help fix broken OCR? In theory, denoising tokens in parallel could work better for OCR correction since context is seen upfront? Pointed it at 19th-century newspaper OCR. It corrected better than the autoregressive baseline — at ~8x the speed.

Daniel van Strien

36,105 views • 16 days ago

> Waiting at the DMV > Open Claude Code iOS app > "Upgrade my app to Expo SDK 55" > [View PR] > Open in Expo Go > LGTM > Merge PR > CI pushed to production 🚀

> Waiting at the DMV > Open Claude Code iOS app > "Upgrade my app to Expo SDK 55" > [View PR] > Open in Expo Go > LGTM > Merge PR > CI pushed to production 🚀

Evan Bacon 🥓

33,231 views • 5 months ago