Upload 3 files

Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.9-slim
+
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+
+USER root
+RUN rm /var/lib/apt/lists/* -vf
+RUN apt-get clean
+RUN apt-get update
+RUN apt-get upgrade
+RUN apt-get install -y wget zip unzip uvicorn espeak-ng
+USER user
+COPY . .
+USER root
+RUN chmod 777 ~/app/*
+USER user
+
+RUN pip3 install -r requirements.txt
+
+CMD ["python", "app.py"]

app2.py

@@ -0,0 +1,43 @@
+import gradio as gr
+from transformers import pipeline
+from transformers import BlipForQuestionAnswering
+from transformers.utils import logging
+logging.set_verbosity_error()
+
+from transformers import AutoProcessor
+
+
+
+od_pipe = pipeline("object-detection", "facebook/detr-resnet-50")
+tts_pipe = pipeline("text-to-speech",
+                    model="kakao-enterprise/vits-ljs")
+
+model = BlipForQuestionAnswering.from_pretrained(
+    "Salesforce/blip-vqa-base")
+
+processor = AutoProcessor.from_pretrained(
+    "Salesforce/blip-vqa-base")
+
+def get_pipeline_prediction(pil_image, question):
+    
+    inputs = processor(pil_image, question, return_tensors="pt")
+
+    out = model.generate(**inputs)
+
+    text = processor.decode(out[0], skip_special_tokens=True)
+        
+    narrated_text = tts_pipe(text)
+
+        
+    return (narrated_text["sampling_rate"], narrated_text["audio"][0] )
+    
+
+demo = gr.Interface(
+  fn=get_pipeline_prediction,
+  inputs=[gr.Image(label="Input image", 
+                  type="pil"), gr.Textbox(label="Ask your question")],
+  outputs=gr.Audio(label="Narration", type="numpy",  autoplay=True)
+  
+)
+
+demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,7 @@
+opencv-python-headless<4.3
+gradio
+transformers
+phonemizer
+py-espeak-ng
+inflect
+timm