I built an offline Mongolian drafting tool for border-town merchants. Here’s where it breaks.

说明与用途

CLI merchant‑ai‑draft 从中文 JSON 生成蒙古语西里尔字母草稿，但在术语和货币方面存在问题。

问题

Professional translators are slow, expensive, and sometimes unreliable for merchants in Erenhot who need written product information in Mongolian Cyrillic.

结果

The CLI produces native Cyrillic Mongolian drafts in about 3 seconds per sentence on Apple Silicon, but struggles with terminology, currency units, and product clauses. Photo‑to‑description works well in Chinese but translation to Mongolian mangles key terms.

工作流

• 1. Prepare a merchant JSON file in Chinese.
• 2. Run python mn_draft.py --input merchant.json to generate a draft in Cyrillic Mongolian.
• 3. Review the draft; if marked reviewed, the file remains unchanged. The tool enforces AI proposal and human decision in code.
• 4. Use the output as the basis for a bilingual electronic product card.
• 5. Optionally, spike a photo‑to‑description flow with qwen2.5vl:7b for product images.

证据

merchant‑ai‑draft — an offline CLI that takes a merchant JSON file (Chinese copy), fills in Mongolian (Cyrillic) first drafts with a local open‑weight model, and marks everything draft.

来源

NLLB-200-3.3B (selected) outputs Cyrillic Mongolian natively — but terminology, currency units, and clauses remain unreliable. ~3 seconds per sentence on Apple Silicon.

来源

The CLI itself is covered by 11 automated tests (review protection, ID preservation, offline failure handling).

来源