code of the demo

All code for the demo

app.py

@@ -0,0 +1,63 @@
+import gradio as gr
+import requests
+import tensorflow as tf
+from transformers import pipeline
+
+# audio2text
+trans = pipeline("automatic-speech-recognition", model = "facebook/wav2vec2-large-xlsr-53-spanish")
+
+def audio2text(audio):
+  text = trans(audio)["text"]
+  return text
+
+
+# text2sentiment
+classifier = pipeline("text-classification", model = "pysentimiento/robertuito-sentiment-analysis")
+
+def text2sentiment(text):
+  return classifier(text)[0]["label"]
+
+
+# image_classification
+inception_net = tf.keras.applications.MobileNetV2()
+
+answer = requests.get("https://git.io/JJkYN")
+labels = answer.text.split("\n")
+
+def image_classification(inp):
+  inp = inp.reshape((-1,224,224,3))
+  inp = tf.keras.applications.mobilenet_v2.preprocess_input(inp)
+  prediction = inception_net.predict(inp).flatten()
+  confidences = {labels[i]: float(prediction[i]) for i in range(1000)}
+  return confidences
+
+
+# demo
+demo = gr.Blocks()
+
+with demo:
+  gr.Markdown("This is the second demo with Blocks")
+  with gr.Tabs():
+    with gr.TabItem("Transcribe audio in Spanish"):
+      with gr.Row():
+        audio = gr.Audio(source="microphone", type="filepath")
+        transcription = gr.Textbox()
+      b1 = gr.Button("Transcribe")
+
+    with gr.TabItem("Sentiment analysis in Spanish"):
+      with gr.Row():
+        text = gr.Textbox()
+        label_sentiment = gr.Label()
+      b2 = gr.Button("Sentiment")
+
+    with gr.TabItem("Image classification"):
+      with gr.Row():
+        image=gr.Image(shape=(224,224))
+        label_image=gr.Label(num_top_classes=3)
+      b3 = gr.Button("Classify")
+
+    b1.click(audio2text, inputs = audio, outputs=transcription)
+    b2.click(text2sentiment, inputs=text, outputs=label_sentiment)
+    b3.click(image_classification, inputs=image, outputs=label_image)
+
+demo.launch()