Create app.py

app.py

@@ -0,0 +1,35 @@
+# Use a pipeline as a high-level helper
+import torch
+from transformers import pipeline
+from scipy.io import wavfile
+from PIL import Image
+import gradio as gr
+
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+image_pipe  = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large",device=device)
+narator     = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs",device=device)
+
+def generate_audio(text):
+    # generate the audio from the text
+    audio_text = narator(text)    
+    # save the audio to a WAV file 
+    wavfile.write(filename="audio.wav", 
+                  rate=audio_text['sampling_rate'], 
+                  data=audio_text['audio'][0])    
+    return "audio.wav"
+
+
+def caption_my_image(image_path):
+    image = image_pipe(image_path)
+    caption_text = image[0]['generated_text']
+    return generate_audio(caption_text)
+
+
+demo = gr.Interface(fn=caption_my_image,                    
+                    inputs=[gr.Image(label="Image",type="pil")],
+                    outputs=[gr.Audio(label="Image Caption")],
+                    title="@SmartChoiceLearningHubs HF project 1 :Image to Text to Speech",
+                    description="This app generates a caption for an image and converts the caption to speech.")
+
+demo.launch()