init

whisper/Dockerfile

@@ -0,0 +1,19 @@
+FROM python:3.11-slim
+ENV PYTHONUNBUFFERED=1
+WORKDIR /app
+
+# Install system dependencies for audio handling and build tools
+RUN apt-get update && apt-get install -y --no-install-recommends \
+	ffmpeg \
+	libsndfile1 \
+	build-essential \
+	git \
+	wget \
+ && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt ./
+RUN python -m pip install --upgrade pip setuptools wheel && \
+	pip install --no-cache-dir -r requirements.txt
+
+COPY server.py ./
+CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8001"]

whisper/requirements.txt

@@ -0,0 +1,6 @@
+fastapi==0.100.0
+uvicorn[standard]==0.22.0
+whisper==20230314
+pydub==0.25.1
+aiofiles==23.1.0
+python-multipart==0.0.6

whisper/server.py

@@ -0,0 +1,32 @@
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.responses import JSONResponse
+import whisper
+import tempfile
+import shutil
+
+app = FastAPI()
+
+model = whisper.load_model("small")
+
+
+@app.post("/transcribe")
+async def transcribe(file: UploadFile = File(...)):
+    if not file.content_type.startswith("audio"):
+        raise HTTPException(status_code=400, detail="File must be audio")
+
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
+        contents = await file.read()
+        tmp.write(contents)
+        tmp.flush()
+        tmp_path = tmp.name
+
+    try:
+        result = model.transcribe(tmp_path, language=None)
+        text = result.get("text", "")
+    finally:
+        try:
+            shutil.os.remove(tmp_path)
+        except Exception:
+            pass
+
+    return JSONResponse({"text": text})