# Softcatala/whisper-ctranslate2

Whisper command line client compatible with original OpenAI client based on CTranslate2.

Repository: https://github.com/Softcatala/whisper-ctranslate2
Canonical: https://ross.abutalabs.com/products/whisper-ctranslate2
Language: Python
License: MIT
License Family: permissive
Topics: speech-recognition, speech-to-text, whisper, openai-, openai-whisper
Last push: 2026-02-14T19:16:02+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 35, longevity 90
- inputs: {"age_days": 1265, "days_push": 200, "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 1343, forks 128 (observed 2026-08-28T04:04:26.466830+00:00)

## What it is
A command-line transcription and translation tool compatible with OpenAI's Whisper CLI, built on CTranslate2 and faster-whisper for up to 4x faster inference with lower memory usage. It supports GPU and CPU execution, speaker diarization, VAD filtering, live microphone transcription, and custom fine-tuned models.

## Use cases
- transcribe audio files to text from the command line
- translate audio to English like OpenAI Whisper
- run faster whisper transcription with less memory
- transcribe live audio from a microphone
- identify speakers in a recording with diarization
- use my own fine-tuned whisper model
- migrate scripts from openai whisper cli without changes

## When to choose
- you want OpenAI Whisper CLI compatibility with much faster inference
- you need GPU-accelerated or CPU-optimized transcription
- you need speaker diarization or VAD filtering
- you want to run transcription in Docker with preloaded models

## When to avoid
- you need a GUI or web interface rather than a CLI
- you need a Python library API rather than a command-line tool
- you require features from the latest OpenAI Whisper models not supported by CTranslate2

## Facets
- artifact type: cli-tool
- maturity: active
- function: speech-recognition, cli, machine-learning
- domain: speech-processing
- platform: cli, python, cross-platform
- tags: whisper, ctranslate2, transcription, translation, speaker-diarization, faster-whisper, natural-language-processing, command-line, docker

## Member repositories
- Softcatala/whisper-ctranslate2 (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:26.466830+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 2026-08-30T04:42:52.391202+00:00, confidence not recorded.
  - readme: https://github.com/Softcatala/whisper-ctranslate2 (fetched 2026-08-28T04:04:26.466830+00:00, sha d4a337af0e57)
  - registry_pypi: https://pypi.org/pypi/whisper-ctranslate2/json (fetched 2026-08-29T12:02:10.402311+00:00, sha 585708a3990b)
- Data as of 2026-08-30T08:39:29.467469+00:00.