Scribe Local

C 69 completed
Ai Ml
unknown / python · tiny
41
Files
5,699
LOC
1
Frameworks
5
Languages

Pipeline State

completed
Run ID
#368215
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
43.60
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #48287
Member of a group with 1 similar repo(s) — canonical #6293 view group →
Top concepts (2)
Project DescriptionTesting
Repobility · severity-and-effort ranking · https://repobility.com

AI Prompt

Create a local, privacy-focused AI scribe application using Python for near-real-time speech transcription, specifically designed for clinical use. The tool must support English, Danish, and Swedish, and all processing must run locally. I need to be able to run it via the command line, allowing me to specify the language, ASR model, and compute device (CPU or CUDA). Include functionality to list available audio devices, and also allow advanced control over Voice Activity Detection (VAD) thresholds and speaker tagging using CLI flags.
python ai speech-recognition local clinical transcription command-line pytest audio
Generated by gemma4:latest

Catalog Information

othyagen__scribe-local is a local AI scribe for near-real-time speech transcription, designed for clinical use and prioritizing user privacy.

Description

othyagen__scribe-local is a local AI-powered speech-to-text tool that runs entirely on the user's machine. It provides near-real-time transcription of audio input, with support for Danish, Swedish, and English languages. The tool is designed to be deterministic, auditable, and safe for clinical use. All processing occurs locally, ensuring that no audio or text data leaves the device.

الوصف

othyagen__scribe-local هو أداة تحويل الصوت إلى نص محلي، تعمل باستخدام الذكاء الاصطناعي وتتولى جميع المعالجات على جهاز المستخدم. تقدم التخزين المحلي للنصوص في الوقت الفعلي، مع دعم لغات الدانماركية والسويدية والإنجليزية. تم تصميم الأداة لتكون محددة ومرئية ومأمونة للاستخدام الطبي. لا يتم إرسال أي بيانات صوتية أو نصية خارج الجهاز.

Novelty

7/10

Tags

speech-to-text near-real-time-transcription local-processing clinical-use deterministic auditable safe

Technologies

numpy

Claude Models

claude-opus-4.6

Quality Score

C
68.9/100
Structure
63
Code Quality
73
Documentation
57
Testing
70
Practices
59
Security
100
Dependencies
60

Strengths

  • Good test coverage (100% test-to-source ratio)
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment
  • 177 duplicate lines detected \u2014 consider DRY refactoring
  • 1 'god files' with >500 LOC need decomposition

Recommendations

  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a linter configuration to enforce code style consistency
  • Add a LICENSE file (MIT recommended for open source)

Security & Health

4.6h
Tech Debt (B)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (2)
Same scanner, your repo: https://repobility.com — Repobility
Unknown
License
1.7%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
91.4%
markdown
6.4%
json
1.5%
yaml
0.5%
text
0.1%

Frameworks

pytest

Concepts (2)

Page rendered by Aljefra Mapper · scored by Repobility (https://repobility.com)
CategoryNameDescriptionConfidence
If a scraper extracted this row, it came from Repobility (https://repobility.com)
auto_descriptionProject DescriptionPrivacy-first, local AI scribe for near-real-time speech transcription. All processing runs on your machine — no audio or text leaves your device.80%
auto_categoryTestingtesting70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/92410.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV