Josh Knapp
532de77927
Some checks failed
Build App / compute-version (pull_request) Successful in 3s
Build App / build-macos (pull_request) Successful in 2m28s
Build STT Container / build-stt-container (pull_request) Successful in 3m18s
Build App / build-windows (pull_request) Successful in 4m40s
Build App / build-linux (pull_request) Failing after 1m46s
Build App / create-tag (pull_request) Has been skipped
Build App / sync-to-github (pull_request) Has been skipped
Adds a mic button to the terminal UI that captures speech, transcribes it via a Faster Whisper sidecar container, and injects the text into the terminal input. Includes settings panel for model selection (tiny/small/medium), port config, and container lifecycle management. - stt-container/: Dockerfile + FastAPI server for Whisper transcription - Rust backend: STT container management, transcribe_audio IPC command - Frontend: useSTT hook, SttButton, SttSettings, WAV encoder - CI: Gitea Actions workflow for multi-arch STT image builds Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
42 lines
1.1 KiB
Python
42 lines
1.1 KiB
Python
import os
|
|
import tempfile
|
|
|
|
from faster_whisper import WhisperModel
|
|
from fastapi import FastAPI, File, Form, UploadFile
|
|
from fastapi.responses import JSONResponse
|
|
|
|
app = FastAPI()
|
|
model: WhisperModel | None = None
|
|
|
|
|
|
@app.on_event("startup")
|
|
def load_model():
|
|
global model
|
|
model_size = os.environ.get("WHISPER_MODEL", "tiny")
|
|
model = WhisperModel(model_size, device="cpu", compute_type="int8")
|
|
|
|
|
|
@app.post("/transcribe")
|
|
async def transcribe(
|
|
file: UploadFile = File(...),
|
|
language: str = Form(None),
|
|
):
|
|
if model is None:
|
|
return JSONResponse(status_code=503, content={"error": "Model not loaded"})
|
|
|
|
with tempfile.NamedTemporaryFile(suffix=".wav", delete=True) as tmp:
|
|
tmp.write(await file.read())
|
|
tmp.flush()
|
|
kwargs = {}
|
|
if language:
|
|
kwargs["language"] = language
|
|
segments, info = model.transcribe(tmp.name, **kwargs)
|
|
text = " ".join(s.text for s in segments).strip()
|
|
|
|
return {"text": text, "language": info.language}
|
|
|
|
|
|
@app.get("/health")
|
|
def health():
|
|
return {"status": "ok"}
|