# elanmart/cbp-translate

Repository: https://github.com/elanmart/cbp-translate
Canonical: https://ross.abutalabs.com/products/cbp-translate
Language: Python
License: MIT
License Family: permissive
Last push: 2023-01-02T14:34:46+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 97
- inputs: {"age_days": 1361, "days_push": 1339, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1274, forks 51 (observed 2026-08-28T04:04:12.715314+00:00)

## What it is
A demo application that live-translates foreign-language speech in videos into subtitles, mimicking the Cyberpunk 2077 translation effect. It combines Whisper for transcription, NVIDIA NeMo for speaker diarization, DeepL for translation, and face detection to attribute phrases to on-screen speakers.

## Use cases
- add translated subtitles to a video clip
- transcribe and translate speech from an interview video
- identify which speaker said which phrase in a video
- recreate the cyberpunk 2077 live translation effect
- diarize speakers in a multi-person recording
- translate polish speech to english automatically

## When to avoid
- you need production-grade, highly accurate diarization and translation
- you need real-time live translation of streams
- you want a polished end-user product rather than a demo

## Facets
- artifact type: application
- maturity: maintenance
- function: speech-recognition, video-processing, machine-learning, nlp, computer-vision
- domain: speech-processing, machine-learning, deep-learning
- platform: python, cloud
- tags: subtitles, translation, speaker-diarization, whisper, deepl, face-detection, cyberpunk-2077, poc, video, natural-language-processing, docker

## Member repositories
- elanmart/cbp-translate (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:12.715314+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:03:07.171076+00:00, confidence not recorded.
  - readme: https://github.com/elanmart/cbp-translate (fetched 2026-08-28T04:04:12.715314+00:00, sha f900fd08d85e)
- Data as of 2026-08-30T08:39:29.467469+00:00.