initial uploads

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.10
+
+WORKDIR /python-docker
+
+COPY requirements.txt requirements.txt
+RUN apt-get update && apt-get install git -y
+RUN pip3 install -r requirements.txt
+RUN pip3 install "git+https://github.com/openai/whisper.git" 
+RUN apt-get update && apt-get install -y ffmpeg
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "fastapi_app:app", "--host", "0.0.0.0", "--port", "8000"]

fastapi_app.py

@@ -0,0 +1,45 @@
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.responses import JSONResponse, RedirectResponse
+from tempfile import NamedTemporaryFile
+import whisper
+import torch
+from typing import List
+
+# Checking if NVIDIA GPU is available
+DEVICE = "cpu"
+
+# Load the Whisper model:
+model = whisper.load_model("base", device=DEVICE)
+
+app = FastAPI()
+
+@app.post("/whisper/")
+async def handler(files: List[UploadFile] = File(...)):
+    if not files:
+        raise HTTPException(status_code=400, detail="No files were provided")
+
+    # For each file, let's store the results in a list of dictionaries.
+    results = []
+
+    for file in files:
+        # Create a temporary file.
+        with NamedTemporaryFile(delete=True) as temp:
+            # Write the user's uploaded file to the temporary file.
+            with open(temp.name, "wb") as temp_file:
+                temp_file.write(file.file.read())
+            
+            # Let's get the transcript of the temporary file.
+            result = model.transcribe(temp.name)
+
+            # Now we can store the result object for this file.
+            results.append({
+                'filename': file.filename,
+                'transcript': result['text'],
+            })
+
+    return JSONResponse(content={'results': results})
+
+
+@app.get("/", response_class=RedirectResponse)
+async def redirect_to_docs():
+    return "/docs"

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+aiofiles
+python-multipart
+uvicorn