Create app.py

app.py

@@ -0,0 +1,43 @@
+import torch
+import gradio as gr
+from PIL import Image
+import scipy.io.wavfile as wavfile
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+# model_path = "../Models/models--Salesforce--blip-image-captioning-base/snapshots/82a37760796d32b1411fe092ab5d4e227313294b"
+# model_path2 = "../Models/models--kakao-enterprise--vits-ljs/snapshots/3bcb8321394f671bd948ebf0d086d694dda95464"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# caption_image = pipeline("image-to-text", model=model_path, device=device)
+caption_image = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base", device=device)
+
+# narrator = pipeline("text-to-speech", model=model_path2)
+narrator = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs")
+
+def generate_audio(text):
+    # Generate the narrated text
+    narrated_text = narrator(text)
+
+    # Save the audio to a WAV file
+    wavfile.write("output.wav", rate=narrated_text["sampling_rate"],
+                  data=narrated_text["audio"][0])
+
+    # Return the path to the saved audio file
+    return "output.wav"
+
+def caption_my_image(pil_image):
+    semantics = caption_image(images=pil_image)[0]['generated_text']
+    return generate_audio(semantics)
+
+gr.close_all()
+
+demo = gr.Interface(fn=caption_my_image,
+                    inputs=[gr.Image(label="Select Image",type="pil")],
+                    outputs=[gr.Audio(label="Generated Caption")],
+                    title="@GenAILearniverse Project 8: Image Captioning",
+                    description="THIS APPLICATION WILL BE USED TO GET THE AUDIO CAPTION OF IMAGE.")
+
+demo.launch()