David Miheev

DeepDavid

1 17

https://davidmiheev.life

davidmiheev

AI & ML interests

Deep RL, Data Science

Recent Activity

liked a model 3 days ago

google/embeddinggemma-2

reacted to GoktugD's post with ❤️ about 2 months ago

🇹🇷 We trained a 1B OCR model specifically for Turkish enterprise documents. **Werea-DocOCR-1B v2** The result surprised us: LightOnOCR-2 base → **64.2% CER** Werea-DocOCR v1 → **~8.1% CER** Werea-DocOCR v2 → **0.15% CER** 🚀 Evaluated on a held-out 72-page test set across 12 Turkish document types and 3 different capture conditions. 📄 12 Turkish enterprise document types 🧪 12,960 synthetic training pages 📱 Digital + scanned + phone photos 📊 Tables → structured Markdown ⚙️ Full-parameter fine-tuning 🖥️ Trained on a single RTX 3090 It handles: • e-Invoices • rental contracts • bank receipts • payroll documents • insurance policies • vehicle documents • official correspondence • trade registry documents • SGK-style tables • and more. **Model 🤗** https://huggingface.co/Werea-co/Werea-DocOCR-1B **Dataset 📚** https://huggingface.co/datasets/Werea-co/werea-tr-doc-ocr-enterprise-v2 **Werea 🇹🇷** https://huggingface.co/Werea-co We're building open AI models from Türkiye. This is just the beginning. #HuggingFace #OCR #DocumentAI #TurkishAI #OpenSourceAI #ComputerVision

liked a model about 2 months ago

Qwen/Qwen3.8-Flash-Next

View all activity

Organizations

liked a model 3 days ago

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 15 days ago • 172k • 2.78k

reacted to GoktugD's post with ❤️ about 2 months ago

Post

2,395

🇹🇷 We trained a 1B OCR model specifically for Turkish enterprise documents.

**Werea-DocOCR-1B v2**

The result surprised us:

LightOnOCR-2 base → **64.2% CER**
Werea-DocOCR v1 → **~8.1% CER**
Werea-DocOCR v2 → **0.15% CER** 🚀

Evaluated on a held-out 72-page test set across 12 Turkish document types and 3 different capture conditions.

📄 12 Turkish enterprise document types
🧪 12,960 synthetic training pages
📱 Digital + scanned + phone photos
📊 Tables → structured Markdown
⚙️ Full-parameter fine-tuning
🖥️ Trained on a single RTX 3090

It handles:

• e-Invoices
• rental contracts
• bank receipts
• payroll documents
• insurance policies
• vehicle documents
• official correspondence
• trade registry documents
• SGK-style tables
• and more.

**Model 🤗**
Werea-co/Werea-DocOCR-1B

**Dataset 📚**
Werea-co/werea-tr-doc-ocr-enterprise-v2

**Werea 🇹🇷**

Werea-co

We're building open AI models from Türkiye.

This is just the beginning.

#HuggingFace #OCR #DocumentAI #TurkishAI #OpenSourceAI #ComputerVision