Загрузка видео...

Не удалось загрузить видео

На главную

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_pachaar's profile picture

Akshay 🚀

261,984 subscribers

45,427 просмотров • 4 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

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
1:20

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⚡

119,771 просмотров • 13 дней назад

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.
0:33

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 🚀

251,920 просмотров • 9 месяцев назад

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.
0:29

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 просмотров • 4 месяцев назад

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
1:12

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 просмотров • 7 месяцев назад

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
0:38

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 просмотров • 6 месяцев назад

launching our open source OCR tool today! try it out with some terrible pdfs and let me know how it goes:
0:31

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

Tyler Maran

342,460 просмотров • 1 год назад

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 🫡
0:57

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 просмотров • 11 месяцев назад

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.
0:22

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 🚀

477,634 просмотров • 1 год назад

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.
0:43

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

208,470 просмотров • 1 день назад

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 👀
0:30

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 просмотров • 7 месяцев назад

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)
1:28

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

49,362 просмотров • 7 месяцев назад

> 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
0:58

> 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 просмотров • 7 месяцев назад

I just made an open-source version of Dhruv Rathee AI startup. > Even with more models :) Link in comments
0:45

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

Humi

202,602 просмотров • 9 месяцев назад

wow, total BoM cost $660, folks open-source community >> closed source hyped robots
2:00

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

Thomas Wolf

192,459 просмотров • 9 месяцев назад

> checking indicators. > watching the 1s chart. > position opened. > session complete. Agent Trade Kit. Open source. Local-first. Live now.
0:25

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

OKX

32,694 просмотров • 2 месяцев назад

> 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 🚀
0:33

> 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 просмотров • 4 месяцев назад

Introducing the new evolution of Open Campus We believe you can 1000x your success when you 10x your focus > 1 month -> 1 year, online support + meet IRL 3 times > 10 projects -> 3 projects > General app -> consumer crypto > $100k in funding -> keeping that Applications open
0:40

Introducing the new evolution of Open Campus We believe you can 1000x your success when you 10x your focus > 1 month -> 1 year, online support + meet IRL 3 times > 10 projects -> 3 projects > General app -> consumer crypto > $100k in funding -> keeping that Applications open

OE

43,751 просмотров • 7 месяцев назад

Jennifer as kumud>>>>> One of the best female characters in ITV
0:22

Jennifer as kumud>>>>> One of the best female characters in ITV

َ

91,512 просмотров • 3 лет назад

bytedance just released BAGEL! an open-source multimodal alternative to gpt-4o and gemini flash it supports: > image reasoning > image editing > video generation > style transfer (ghiblify anyone?) > 3d rotation > outpainting > navigation
1:17

bytedance just released BAGEL! an open-source multimodal alternative to gpt-4o and gemini flash it supports: > image reasoning > image editing > video generation > style transfer (ghiblify anyone?) > 3d rotation > outpainting > navigation

Dreaming Tulpa 🥓👑

257,947 просмотров • 1 год назад

KIMI K2.5 JUST MOGGED EVERYONE. > 1T PARAMETERS. > NATIVE MULTI MODAL. > BEATS CLAUDE 4.5 OPUS. > OPEN SOURCE.
0:29

KIMI K2.5 JUST MOGGED EVERYONE. > 1T PARAMETERS. > NATIVE MULTI MODAL. > BEATS CLAUDE 4.5 OPUS. > OPEN SOURCE.

sui ☄️

394,521 просмотров • 4 месяцев назад