why smote raise "Found input variables with inconsistent numbers of samples"?

I try to classify emotion from tweet with dataset of 4401 tweet, when i use smaller sample of data (around 15 tweet) everything just work fine, but when i use the full dataset it raise the error of

Found input variables with inconsistent numbers of samples: [7, 3520]

the error happen when i try to oversampling the data using smote after transforming the data using countvectorizer.

This is the code where the error raise

# N-gram Feature and Term Frequency
vectorizer = CountVectorizer(ngram_range=(1,3))
x_train_tf = vectorizer.fit_transform(str(x_train).split('n')).toarray()
x_test_tf = vectorizer.transform(str(x_test).split('n')).toarray()
df_output = pd.DataFrame(data =x_train_tf, columns = vectorizer.get_feature_names_out())
display(df_output)
# the print shape is (7 rows × 250 columns)

smote = SMOTE(random_state=42, k_neighbors=5)
x_smote, y_smote = smote.fit_resample(x_train_tf, y_train)
print("Total Train Data SMOTE : ",x_smote.shape), print("Total Train Label SMOTE : ",y_smote)

i did not understand why this is happening so some explanation could really help.
i already tried to solve it using answers from other similiar question but nothing have worked.

This is the full code

import nltk
import re
#nltk.download()
import string
import numpy as np
import pandas as pd 
import matplotlib.pyplot as plt
from nltk import everygrams
from collections import Counter
from sklearn import preprocessing
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from imblearn.over_sampling import SMOTE
from sklearn.naive_bayes import GaussianNB
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from Sastrawi.Stemmer.StemmerFactory import StemmerFactory
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics import accuracy_score, recall_score, precision_score, f1_score, confusion_matrix

dataset = pd.read_csv("G:/TA/Program/dataset/Twitter_Emotion_Dataset.csv", encoding='latin-1')
# Preprocessing
dataset['case_folding_tweet'] = dataset['tweet'].str.casefold()
dataset['only_alphabet_tweet'] = [re.sub('[^a-zA-Z]+s*', ' ', s) for s in dataset['case_folding_tweet']]
dataset['data_cleaning_tweet'] = dataset['only_alphabet_tweet'].str.replace(r'bw{1}b','').str.replace(r's+', ' ')

slangword_dictionary = ("G:/TA/Program/dataset/kamus_singkatan.csv")

deslang = {}
list_slangword = open(slangword_dictionary).readlines()
for line in list_slangword:
    slang, unslang = line.strip().split(';')
    deslang[slang] = unslang
deslang[slang] = {r"b{}b".format(k): v for k, v in deslang.items()}

dataset['data_cleaning_tweet'] = dataset['data_cleaning_tweet'].replace(deslang[slang], regex=True)
dataset['convert_slang_tweet'] = dataset['data_cleaning_tweet']

replace_dictionary = {'tidak ': 'tidak', 'bukan ': 'bukan', 'jangan ': 'jangan', 'belum ': 'belum'}
dataset['convert_negation_tweet'] = dataset['convert_slang_tweet'].replace(replace_dictionary, regex=True)
dataset['tokenization_tweet'] = dataset['convert_negation_tweet'].apply(word_tokenize) 
list_stopwords = set(stopwords.words("indonesian"))
list_stopwords.add('username')
list_stopwords.add('url')
dataset['stopword_removal_tweet'] = dataset['tokenization_tweet'].apply(lambda x: [item for item in x if item not in list_stopwords])

factory = StemmerFactory()
stemmer = factory.create_stemmer()
dataset['stemmed_tweet'] = dataset['stopword_removal_tweet'].apply(lambda x: [stemmer.stem(y) for y in x]) 

# Split data
x = dataset["stemmed_tweet"].values
y = dataset["label"].values
x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.8, random_state= 42)

# Get N-gram and TF
vectorizer = CountVectorizer(ngram_range=(1,3))
x_train_tf = vectorizer.fit_transform(str(x_train).split('n')).toarray()
x_test_tf = vectorizer.transform(str(x_test).split('n')).toarray()

# Oversampling
smote = SMOTE(random_state=42, k_neighbors=5)
x_smote, y_smote = smote.fit_resample(x_train_tf, y_train)

print("Total Train Data SMOTE : ",x_smote.shape), print("Total Train Label SMOTE : ",y_smote)

gnb_classifier = GaussianNB()
gnb_classifier.fit(x_smote, y_smote)
print(gnb_classifier)
y_pred = gnb_classifier.predict(x_test_tf)
print("Emotion Predicted :", y_pred)

Link to the dataset