Update app.py

app.py

@@ -5,19 +5,19 @@ import librosa
 
 checkpoint = "openai/whisper-base"
 # checkpoint = "/innev/open-ai/huggingface/openai/whisper-base"
-processor = WhisperProcessor.from_pretrained(checkpoint)
-model = WhisperForConditionalGeneration.from_pretrained(checkpoint)
-text_Interface=gr.Interface.load("models/nlpconnect/vit-gpt2-image-captioning")
+image_to_text_model = pipeline("image-classification")
+text_to_audio_model = pipeline("text-to-speech")
 
-def greet():
-    return "Hello "
+def image_to_text(input_image):
+    # Convertir la imagen a texto
+    text_output = image_to_text_model(input_image)[0]['label']
+    return text_output
 
 with gr.Blocks() as demo:
     gr.Markdown("Start typing below and then click **Run** to see the output.")
     with gr.Row():
         inp = gr.Image(type='pil')
-        out = gr.Textbox()
-    gr.Interface(fn=greet, inputs=inp, outputs=out)
+        out = gr.Textbox(placeholder=image_to_text(inp))
+    gr.Interface(fn=image_to_text, inputs=inp, outputs=[out])
 
 demo.launch()
-text_Interface.launch()