Rename project_2b.py to app.py

project_2b.py → app.py

@@ -1,11 +1,21 @@
-# -*- coding: utf-8 -*-
-"""Project 2B.ipynb
+import streamlit as st
+import os
+import os
+os.system('pip install transformers')
+import os
+os.system('pip install torch')
+import os
+os.system('pip install tensorflow')
+import os
+os.system('pip install soundfile')
+import soundfile as sf
 
-Automatically generated by Colab.
+from transformers import VitsModel, AutoTokenizer
+import numpy as np
+import io
 
-Original file is located at
-    https://colab.research.google.com/drive/1DZjrQCfQQ3LfSVDKMae3N7I_wKQU3c9a
-"""
+import torch
+print(torch.__version__)
 
 import pandas as pd
 from sklearn.model_selection import train_test_split
@@ -21,58 +31,62 @@ from wordcloud import WordCloud
 import zipfile
 import os
 
-df = pd.read_csv("sample_data/Restaurant_Reviews.tsv", sep='\t')
-df=df.head(200)
-df.shape
-
-df.head()
-
-sns.countplot(x='Liked', data=df)
-plt.title('Sentiment Distribution (0 = Negative, 1 = Positive)')
-plt.show()
-
-example=df['Review'][56]
-example
-
-vectorizer = TfidfVectorizer(max_features=5000)
-X = vectorizer.fit_transform(df['Review'])
-y = df['Liked']
-
-
-
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
-
-
-
-model = LogisticRegression()
-model.fit(X_train, y_train)
-
-
-
-y_pred = model.predict(X_test)
-print(classification_report(y_test, y_pred))
-
-cm = confusion_matrix(y_test, y_pred)
-sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=model.classes_, yticklabels=model.classes_)
-plt.xlabel('Predicted')
-plt.ylabel('Actual')
-plt.title('Confusion Matrix')
-plt.show()
-
-
-
-import ipywidgets as widgets
-from IPython.display import display
-
-def predict_sentiment(review):
-    # Transform the input review using the vectorizer
-    input_vector = vectorizer.transform([review])
-
-    # Predict sentiment
-    prediction = model.predict(input_vector)[0]
-
-    # Return the sentiment prediction
-    return "Positive" if prediction == 1 else "Negative"
+model = VitsModel.from_pretrained("facebook/mms-tts-eng")
+tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
+
+def generate_speech(text):
+    df = pd.read_csv("sample_data/Restaurant_Reviews.tsv", sep='\t')
+    df=df.head(200)
+    df.shape
+    
+    df.head()
+    
+    sns.countplot(x='Liked', data=df)
+    plt.title('Sentiment Distribution (0 = Negative, 1 = Positive)')
+    plt.show()
+    
+    example=df['Review'][56]
+    example
+    
+    vectorizer = TfidfVectorizer(max_features=5000)
+    X = vectorizer.fit_transform(df['Review'])
+    y = df['Liked']
+    
+    
+    
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+    
+    
+    
+    model = LogisticRegression()
+    model.fit(X_train, y_train)
+    
+    
+    
+    y_pred = model.predict(X_test)
+    print(classification_report(y_test, y_pred))
+    
+    cm = confusion_matrix(y_test, y_pred)
+    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=model.classes_, yticklabels=model.classes_)
+    plt.xlabel('Predicted')
+    plt.ylabel('Actual')
+    plt.title('Confusion Matrix')
+    plt.show()
+    
+    
+    
+    import ipywidgets as widgets
+    from IPython.display import display
+    
+    def predict_sentiment(review):
+        # Transform the input review using the vectorizer
+        input_vector = vectorizer.transform([review])
+    
+        # Predict sentiment
+        prediction = model.predict(input_vector)[0]
+    
+        # Return the sentiment prediction
+        return "Positive" if prediction == 1 else "Negative"
 
 # Text input widget
 review_input = widgets.Text(