Demo with 3 tabs

app.py

@@ -0,0 +1,52 @@
+import requests
+from numpy import asarray
+import gradio as gr
+from transformers import pipeline
+
+answer = requests.get("https://git.io/JJkYN")
+labels =answer.text.split("\n")
+
+def classify_image(inp): 
+  inp = asarray(inp.resize((224, 224)))
+  inp = inp.reshape((-1,) + inp.shape) 
+  inp = tf.keras.applications.mobilenet_v2.preprocess_input(inp) 
+  prediction = inception_net.predict(inp).flatten() 
+  confidences = {labels[k]: float(prediction[k]) for k in range(1000)} 
+  return confidences
+
+def audio_to_text(audio):
+  text = transcribe(audio)["text"]
+  return text
+
+def text_to_sentiment(text):
+  return classifier(text)[0]["label"]
+
+
+demo = gr.Blocks()
+
+with demo:
+  gr.Markdown("Example with Gradio Blocks")
+  with gr.Tabs():
+    with gr.TabItem("Transcribe audio in Spanish"):
+      with gr.Row():
+        audio = gr.Audio(sources="microphone", type="filepath")
+        transcription = gr.Textbox()
+      transcribeButton = gr.Button("Transcribe")
+
+    with gr.TabItem("Sentiment analysis in English and Spanish"):
+      with gr.Row():
+        text = gr.Textbox()
+        label = gr.Label()
+      sentimentButton = gr.Button("Calculate sentiment")
+
+    with gr.TabItem("Image Classification"):
+      with gr.Row():
+        image = gr.Image(label="Upload an image here")
+        label_image = gr.Label(num_top_classes=3)
+      classifyButton = gr.Button("Classify image")
+
+    transcribeButton.click(audio_to_text, inputs = audio, outputs=transcription)
+    sentimentButton.click(text_to_sentiment, inputs=text, outputs=label)
+    classifyButton. click(classify_image, inputs=image, outputs=label_image)
+
+demo.launch()