init

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.11-slim
+COPY . .
+WORKDIR /
+RUN apt-get update && apt-get install -y ffmpeg
+
+RUN ffmpeg -version
+RUN pip install --upgrade pip setuptools wheel 
+RUN pip install -r requirements.txt
+
+ENV OPENAI_API_KEY=${OPENAI_API_KEY}
+
+ENV TRANSFORMERS_CACHE=/transformers_cache
+RUN mkdir -p  /transformers_cache && chmod -R 777  /transformers_cache
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,29 @@
+import os
+from fastapi import FastAPI, HTTPException
+from io import BytesIO
+import requests
+from models import InsertedLink, ExtractedText
+import extractor
+
+os.environ['TRANSFORMERS_CACHE'] = '/transformers_cache'
+os.environ['HF_HOME'] = '/transformers_cache'
+
+
+app =  FastAPI()
+@app.get("/", response_model=dict[str, str])
+def getall():
+    return {"hello":"world"}
+
+
+@app.post("/speech2text", response_model=ExtractedText)
+async def extract(link: InsertedLink):
+    response = requests.get(link.link)
+    if response.status_code == 200:
+        # Open the PDF from bytes in memory
+        mp3 = (BytesIO(response.content))
+    else:
+        #return error, make 500 because file server error
+        raise HTTPException(status_code=response.status_code, detail="File server error")
+
+    dictresult = extractor.speech2text(mp3)
+    return dictresult

extractor.py

@@ -0,0 +1,3 @@
+
+def speech2ytext(mp3):
+    return {"text": "text"}

models.py

@@ -0,0 +1,9 @@
+from pydantic import BaseModel, Field
+from typing import List, Optional, Any
+
+
+class InsertedLink(BaseModel):
+    link: str
+
+class ExtractedText(BaseModel):
+    text: str

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+transformers
+uvicorn[standard]
+openai-whisper
+setuptools-rust
+pydantic