diff --git a/api/DataProcesser.py b/api/DataProcesser.py
index 06353468..9c293e5e 100644
--- a/api/DataProcesser.py
+++ b/api/DataProcesser.py
@@ -14,6 +14,7 @@
 
 import nltk
 from nltk.corpus import stopwords
+nltk.download('stopwords')
 # mais imports
 
 class DataProcesser():
diff --git a/api/Neural_Network2.py b/api/Neural_Network2.py
index 4c06fab4..af37a1bc 100644
--- a/api/Neural_Network2.py
+++ b/api/Neural_Network2.py
@@ -4,14 +4,18 @@
 import pandas as pd
 import numpy as np
 import tensorflow as tf
+import os
 import joblib
 
+from sklearn.feature_extraction.text import TfidfVectorizer
+
 from tensorflow.python.keras import layers
-from tensorflow.python.keras.layers import TextVectorization
 from tensorflow.python.keras.models import Sequential
 from sklearn.preprocessing import LabelEncoder
 from tensorflow.python.keras.callbacks import Callback
 
+dirname = os.path.dirname(__file__)
+
 def preprocess_text(text):
     text = text.lower()
     text = re.sub('\[.*?\]', '', text)
@@ -75,41 +79,28 @@ def create_and_train_model(train_texts, train_labels, name, epochs=5, batch_size
     num_classes = len(label_encoder.classes_)
     train_labels_one_hot = tf.keras.utils.to_categorical(train_labels_encoded, num_classes=num_classes)
 
+    #label_mapping_file = os.path.join(dirname, rf"api/encoders/LabelMapping-{name}.joblib")
     label_mapping_file = f"api/encoders/LabelMapping-{name}.joblib"
     joblib.dump(label_encoder, label_mapping_file)
 
+    tfidf_vectorizer = TfidfVectorizer(max_features=20000)
+    train_texts_tfidf = tfidf_vectorizer.fit_transform(train_texts)
+
     # Cria um conjunto de dados de texto usando a API de conjuntos de dados do TensorFlow
-    train_dataset = tf.data.Dataset.from_tensor_slices((train_texts, train_labels_one_hot))
+    train_dataset = tf.data.Dataset.from_tensor_slices((train_texts_tfidf.toarray(), train_labels_one_hot))
 
     # Embaralha e agrupa os dados
     train_dataset = train_dataset.shuffle(len(train_texts)).batch(32)
 
     # Parâmetros do modelo
-    max_features = 20000
-    embedding_dim = 128
-    sequence_length = 500
-
-    # Cria uma camada de vetorização de texto
-    vectorize_layer = TextVectorization(
-        max_tokens=max_features,
-        output_mode="int",
-        output_sequence_length=sequence_length,
-    )
-
-    # Adapta a camada de vetorização ao conjunto de dados de texto
-    vectorize_layer.adapt(train_dataset.map(lambda x, y: x))
+    num_features = train_texts_tfidf.shape[1]
 
     # Define a arquitetura do modelo
     model = tf.keras.Sequential([
-        vectorize_layer,
-        layers.Embedding(max_features, embedding_dim),
-        layers.Conv1D(128, 7, padding="valid", activation="relu", strides=3),
-        layers.Conv1D(128, 7, padding="valid", activation="relu", strides=3),
-        layers.GlobalMaxPooling1D(),
-        layers.Dense(128, activation="relu"),
-        layers.Dropout(0.5),
-        layers.Dense(num_classes, activation="softmax", name="predictions")
+        tf.keras.layers.Dense(64, activation='relu', input_shape=(num_features,)),
+        tf.keras.layers.Dense(num_classes, activation='softmax')
     ])
+
     model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
 
     try:
diff --git a/api/app.py b/api/app.py
index fcf472e6..8b191d03 100644
--- a/api/app.py
+++ b/api/app.py
@@ -24,7 +24,6 @@
 loop = asyncio.get_event_loop()
 
 def run_flask_app():
-    global server_thread
     app.run(host='0.0.0.0', port=5000, debug=True, use_reloader=False)
 
 def shutdown_server():
@@ -73,7 +72,7 @@ def train_model():
         #
         print("\n")
         print("Received data: " + str(len(selected_data))) 
-        print("Recivied label: " + str(len(selected_label)))
+        print("Received label: " + str(len(selected_label)))
         print("Name: " + str(name))
         print("Epochs: " + str(epochs))
         print("Batch Size: " + str(batch_size))
@@ -105,8 +104,11 @@ def get_training_status():
     except FileNotFoundError:
         return jsonify({'training_in_progress': False, 'training_progress': 0})
 
-if __name__ == '__main__':
-    server_thread = threading.Thread(target=run_flask_app)
-    server_thread.start()
-    atexit.register(shutdown_server)
+#@app.teardown_appcontext
+#def teardown_appcontext(error=None):
+    #shutdown_server()
 
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000)
+    #server_thread = threading.Thread(target=run_flask_app)
+    #server_thread.start()
\ No newline at end of file
diff --git a/api/available_classifiers.py b/api/available_classifiers.py
index ec57c317..6541f33d 100644
--- a/api/available_classifiers.py
+++ b/api/available_classifiers.py
@@ -2,7 +2,7 @@
 import pickle
 
 def get_available_classifiers():
-    model_folder = 'api\models'
+    model_folder = 'api/models'
 
     # Verifica se o diretório 'models' existe
     if not os.path.exists(model_folder):