Go to file

mikael-lovqvists-claude-agent 218687b039 Log to stderr when model needs to be downloaded

Checks cache first with local_files_only=True; if the model isn't present
logs "downloading model ..." to stderr before WhisperModel triggers the
actual download.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-06-07 09:07:13 +00:00

examples

Add Node.js WebSocket example scripts

2026-06-07 08:59:38 +00:00

.gitignore

Add stt-server.py: self-contained recording + VAD + transcription process

2026-06-07 08:41:45 +00:00

README.md

Updated readme

2026-06-07 10:17:43 +02:00

setup-venv-local-build.sh

Add WebSocket broadcast to stt-server.py

2026-06-07 08:53:54 +00:00

setup-venv.sh

Add WebSocket broadcast to stt-server.py

2026-06-07 08:53:54 +00:00

stt-server.py

Log to stderr when model needs to be downloaded

2026-06-07 09:07:13 +00:00

README.md

Voice to text interface

Overview

This project aims to provide voice to text using faster-whisper as backend.

Origin

This project started as a vibe-coded experiment but this version is somewhat more hands on.

Setup

Setup venv for python

We will have two different setups here depending on if you want to build ctranslate2 locally or not. This shall be documented.