transcribe-cli

transcribe-cli is a Rust command-line transcription pipeline built on Whisper and CTranslate2.

It supports:

• CPU-optimized transcription
• optional NVIDIA CUDA execution
• automatic Whisper model download into models/
• local files or http/https audio URLs
• streaming transcription modes
• model cleanup commands

Install

From a local checkout:

cargo install --path . --locked

With CUDA support:

cargo install --path . --locked --features cuda

Usage

transcribe-cli --model small audio.mp3
transcribe-cli --model medium --stream audio.flac
transcribe-cli --model tiny https://example.com/audio.wav

Features

• cuda: enable CUDA support with dynamic loading
• cuda-static: enable static CUDA support
• cuda-dynamic-loading: alias for the dynamic CUDA path
• cudnn: enable cuDNN on top of CUDA

Notes

• Whisper models are downloaded automatically on first use.
• By default models are stored in models/ next to the executable unless --models-dir is set.
• Whisper decoding is handled in-project through a local wrapper around CTranslate2 sys::Whisper and Hugging Face tokenizers.