Upload 3 files

Dockerfile

@@ -0,0 +1,23 @@
+# Use official Python image
+FROM python:3.10-slim
+
+# Install dependencies for ffmpeg and WhisperX
+RUN apt-get update && \
+    apt-get install -y git ffmpeg libsndfile1 && \
+    rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy app code
+COPY . .
+
+# Expose port
+EXPOSE 8000
+
+# Run the FastAPI app
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

app.py

@@ -0,0 +1,32 @@
+from fastapi import FastAPI, UploadFile, File
+from fastapi.responses import JSONResponse
+import whisperx
+import torch
+import tempfile
+import shutil
+import os
+
+app = FastAPI()
+
+# Load model globally to avoid reloading for every request
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = whisperx.load_model("medium", device)
+
+@app.post("/transcribe")
+async def transcribe_audio(file: UploadFile = File(...)):
+    try:
+        # Save uploaded audio to temp file
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
+            shutil.copyfileobj(file.file, tmp)
+            temp_audio_path = tmp.name
+
+        # Load and process audio
+        audio = whisperx.load_audio(temp_audio_path)
+        result = model.transcribe(audio, batch_size=16, return_word_timestamps=True)
+
+        # Clean up temp file
+        os.remove(temp_audio_path)
+
+        return JSONResponse(content=result)
+    except Exception as e:
+        return JSONResponse(status_code=500, content={"error": str(e)})

requirements.txt

@@ -0,0 +1,5 @@
+fastapi==0.110.0
+uvicorn[standard]==0.29.0
+torch==2.2.2
+torchaudio==2.2.2
+whisperx @ git+https://github.com/m-bain/whisperx.git