Update app.py

app.py

@@ -6,18 +6,9 @@ import datasets
 from transformers.pipelines.pt_utils import KeyDataset
 from tqdm.auto import tqdm
 
-transcriber = pipeline(model="openai/whisper-large-v2",device_map="auto")
-# checkpoint = "/innev/open-ai/huggingface/openai/whisper-base"
-image_to_text_model = pipeline("image-classification")
-text_to_audio_model = pipeline("text-to-speech")
-pipe_audio = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-base-960h", device=0)
-dataset = datasets.load_dataset("superb", name="asr", split="test")
+image_to_text_model = pipeline("image-classification",model="microsoft/beit-base-patch16-224-pt22k-ft22k")
+
 
-for out in tqdm(pipe(KeyDataset(dataset, "file"))):
-    print(out)
-    # {"text": "NUMBER TEN FRESH NELLY IS WAITING ON YOU GOOD NIGHT HUSBAND"}
-    # {"text": ....}
-    # ....
 def image_to_text(input_image):
     # Convertir la imagen a texto
     text_output = image_to_text_model(input_image)[0]['label']
@@ -25,11 +16,9 @@ def image_to_text(input_image):
     #texts = transcriber(text_output)
     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()
-#        out = gr.Textbox(placeholder=image_to_text(inp))
-#    gr.Interface(fn=image_to_text, inputs=inp, outputs=out,interpretation="default")
-
-#demo.launch()
+gr.Interface.from_pipeline(pipe, 
+                           title="22k Image Classification",
+                           description="Object Recognition using Microsoft BEIT",
+                           examples = [],
+                           article = "Author: <a href=\"https://huggingface.co/rowel\">Rowel Atienza</a>",
+                           ).launch()