Update app.py

app.py

@@ -1,65 +1,53 @@
-'''Imports'''
+import gradio as gr
 import tensorflow as tf
-#import requests
 from transformers import pipeline
-import gradio as gr
 
-'''Config inception'''
 inception_net = tf.keras.applications.MobileNetV2()
-
-'''Making request and set database'''
-#response = requests.get("https://git.io/JJkYN")
-#tags = response.text.split("\n")
-
-'''Define model and classify pipelines'''
-trans = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-large-xlsr-53-spanish")
-classify = pipeline("text-classification", model="pysentimiento/robertuito-sentiment-analysis")
-
-'''Define functions for demo'''
-def classify_image(inp):
+def classify_imagen(inp):
   inp = inp.reshape((-1, 224, 224, 3))
   inp = tf.keras.applications.mobilenet_v2.preprocess_input(inp)
   prediction = inception_net.predict(inp).reshape(1,1000)
   pred_scores = tf.keras.applications.mobilenet_v2.decode_predictions(prediction, top=100)
-  #prediction = inception_net.predict(inp).flatten()
-  confidences = {f'{pred_scores[0][i][1]}': float(pred_scores[0][i][2]) for i in range(100)}
-  #confidences = {tags[i]: float(prediction[i]) for i in range(1000)}
-  return confidences
+  confidence = {f'{pred_scores[0][i][1]}': float(pred_scores[0][i][2]) for i in range(100)}  
+  return confidence
 
-def audio_to_text(audio):
+trans = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-large-xlsr-53-spanish")
+def audio2text(audio):
   text = trans(audio)["text"]
   return text
+    
+classificator = pipeline("text-classification", model="pysentimiento/robertuito-sentiment-analysis")
+def text2sentiment(text):
+  return classificator(text)[0]['label']
 
-def text_to_sentiment(text):
-  return classify(text)[0]["label"]
 
-'''Define blocks for demo'''
 demo = gr.Blocks()
 
-'''Making demo'''
 with demo:
-  gr.Markdown("Second Demo with Blocks")
+  gr.Markdown("Este es el segundo demo con Blocks hecho por Rafa")
   with gr.Tabs():
-    with gr.TabItem("Transcript audio in spanish"):
+
+    with gr.TabItem("Transcribe Audio en español"):
       with gr.Row():
-        audio = gr.Audio(source="microphone", type="filepath")
-        transcription = gr.Textbox()
-      button1 = gr.Button("Please transcript")
+        audio = gr.Audio(source='microphone', type='filepath')
+        transcript = gr.Textbox()
+      b1 = gr.Button("Transcribe")
 
-    with gr.TabItem("Sentiment analisys"):
+    with gr.TabItem("Analisis de sentimientos"):
       with gr.Row():
-        text = gr.Textbox()
+        texto = gr.Textbox()
         label = gr.Label()
-      button2 = gr.Button("Please sentiment")
+      b2 = gr.Button("Sentimientos")
 
-    with gr.TabItem("Image classify"):
+    b1.click(audio2text, inputs=audio, outputs=transcript)
+    b2.click(text2sentiment, inputs=texto, outputs=label)
+
+    with gr.TabItem("Clasificador de imagenes"):
       with gr.Row():
-        image = gr.Image(shape=(224,224))
-        labelImage = gr.Label(num_top_classes=3)
-      button3 = gr.Button("Please classify Image")
-    
-    button1.click(audio_to_text, inputs=audio, outputs=transcription)
-    button2.click(text_to_sentiment, inputs=text, outputs=label)
-    button3.click(classify_image, inputs=image, outputs=labelImage)
+        image = gr.Image(shape=(224, 224))
+        label= gr.Label(num_top_classes=3)
+      bimage= gr.Button("Clasificar")
+
+    bimage.click(classify_imagen, inputs=image, outputs=label)
 
 demo.launch()