Softcatala/whisper-ctranslate2

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1343 stars · 128 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

cli-tool · maturity active

speech-recognition cli machine-learning speech-processing cli python cross-platform whisper ctranslate2 transcription translation speaker-diarization faster-whisper natural-language-processing command-line docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Softcatala/whisper-ctranslate2")