Add all necessary files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,171 @@
+import gradio as gr
+import tensorflow as tf
+import pickle
+import unicodedata
+import contractions
+import re
+import nltk
+import pandas as pd
+import numpy as np
+from nltk.corpus import stopwords, words
+from nltk.stem import WordNetLemmatizer
+from tensorflow.keras.models import load_model #type:ignore
+from tensorflow.keras.utils import pad_sequences # type: ignore
+
+nltk.download('words')
+nltk.download('punkt_tab')
+nltk.download('wordnet')
+nltk.download('stopwords') 
+
+lemmatizer = WordNetLemmatizer()
+stop_words = set(stopwords.words('english'))
+english_words = set(words.words())
+
+def loadCustomDict(path):
+    with open(path, 'r') as file:
+        return set(line.strip().lower() for line in file if line.strip())
+
+def normalizeWhitespace(text):
+    text = unicodedata.normalize('NFKC', text)
+    text = contractions.fix(text)
+    text = re.sub(r'[\t\r]+', ' ', text) # Menghapus tab
+    text = re.sub(r'\b\d+\b', '', text) # Menghilangkan angka
+    text = re.sub(r'[-‐‑‒–—―]+', '', text)
+    text = re.sub(r'[_﹍﹎＿]', '', text)
+    text = re.sub(r'[^\w\s]', '', text) # Hilangkan symbol punctuation
+    text = re.sub(r'\b(\w+)(?:\s+\1\b)+', r'\1', text)
+    text = re.sub(r'\s+', ' ', text).strip().lower()
+    return text
+
+def removeOtherLanguage(text):
+    phrase = ' translated'
+    pos = text.find(phrase)
+    if pos != -1:
+        text = text[:pos].rstrip()
+    text = re.sub(r'\b\w*[^\x00-\x7F]\w*\b', '', text)
+    text = re.sub(r'\s+', ' ', text).strip().lower()
+    return text
+
+def removeNonEnglish(text_series, custom_dict):
+    pattern = r'\b(?:' + '|'.join(re.escape(word) for word in custom_dict) + r')\b'
+    temp_series = text_series.str.replace(pattern, '', case=False, regex=True)
+    split_words = temp_series.str.split()
+    exploded = split_words.explode()
+    exploded = exploded[exploded.str.lower().isin(english_words)]
+    filtered = exploded[~exploded.str.lower().isin(stop_words)]
+    lemmatized = filtered.apply(lambda word: lemmatizer.lemmatize(word.lower()))
+    cleaned_text_series = lemmatized.groupby(level=0).agg(' '.join)
+    pattern2 = r'\b(\w+)(?:\s+\1\b)+' #, r'\1', text)
+    ser = cleaned_text_series.reindex(text_series.index, fill_value='')
+    text = ser.str.replace(pattern2, r'\1', case=False, regex=True)
+    return text
+
+def cleanInference(df):
+    custom_dict = loadCustomDict('custom_vocab.txt')
+    df['poem'] = df['poem'].apply(normalizeWhitespace)
+    df['poem'] = df['poem'].apply(removeOtherLanguage)
+    df['poem'] = removeNonEnglish(df['poem'], custom_dict)
+    return df
+
+def kerasTokenizer(text, tokenizer):
+    text_sequence = tokenizer.texts_to_sequences(text)
+    text_padded = pad_sequences(text_sequence, maxlen=128)
+    return text_padded
+
+def getLabelEncoder(name):
+    hartmann = ['sadness', 'fear', 'anger', 'joy', 'neutral', 'surprise', 'disgust']
+    savani = ['joy', 'sadness', 'anger', 'fear', 'love', 'surprise']
+    deepseek = ['other', 'sadness', 'joy', 'hope', 'love']
+    if name=='hartmann':
+        return {i : label for i, label in enumerate(sorted(hartmann))}
+    if name=='savani':
+        return {i : label for i, label in enumerate(sorted(savani))}
+    if name=='deepseek':
+        return {i : label for i, label in enumerate(sorted(deepseek))}
+    
+with open(f"tokenizer_savani_0.1_lstm.pkl", "rb") as f:
+    tokenizer_savani = pickle.load(f)
+with open(f"tokenizer_hartmann_0.1_lstm.pkl", "rb") as g:
+    tokenizer_hartman = pickle.load(g)
+with open(f"tokenizer_deepseek_0.1_lstm.pkl", "rb") as h:
+    tokenizer_deepseek = pickle.load(h)
+
+model_savani = load_model(f"best_model_savani_0.1_lstm.keras")
+model_hartman = load_model(f"best_model_hartmann_0.1_lstm.keras")
+model_deepseek = load_model(f"best_model_deepseek_0.1_lstm.keras")
+
+MODELS = {
+    "savani": {
+        "model": model_savani,
+        "tokenizer": tokenizer_savani
+    },
+    "hartmann": {
+        "model": model_hartman,
+        "tokenizer": tokenizer_hartman
+    },
+    "deepseek": {
+        "model": model_deepseek,
+        "tokenizer": tokenizer_deepseek
+    },
+}
+
+loaded_models = {}
+
+def load_model(model_name):
+    if model_name not in loaded_models:
+        tokenizer = MODELS[model_name]['tokenizer']
+        model = MODELS[model_name]['model']
+        loaded_models[model_name] = (tokenizer, model)
+    return loaded_models[model_name]
+    
+
+def predict_poem(poem, model_name):
+    tokenizer, model = load_model(model_name)
+    poem_df = pd.DataFrame({'poem' : [poem]})
+    clean_poem_df = cleanInference(poem_df)
+    text_keras = kerasTokenizer(clean_poem_df['poem'], tokenizer)
+    result = model.predict(text_keras, verbose=0)
+    predicted_labels = np.argmax(result, axis=1)
+    dic = getLabelEncoder(model_name)
+    return dic[predicted_labels[0]]
+
+with gr.Blocks(title="NLP Model Text Classifier") as demo:
+    gr.Markdown("# 📜 Poem Emotion Classification")
+    gr.Markdown("""
+    - ## **Step 1:** Select a labeling technique (model - each has different emotion labels)  
+    - ## **Step 2:** Enter your poem text  
+    - ## **Output:** Predicted emotion with confidence score 
+    """)
+    with gr.Row():
+        with gr.Column():
+            model_selector = gr.Dropdown(
+                choices=list(MODELS.keys()),
+                value="savani",
+                interactive=True,
+                label="Select Labelling Technique Model"
+            )
+            text_input = gr.Textbox(
+                lines=5,
+                placeholder="Enter text here...",
+                label="Input Text",
+                interactive=True
+            )
+            submit_btn = gr.Button("Classify", variant="primary")
+        
+        with gr.Column():
+            output_label = gr.Label(label="Classification Results")
+            gr.Markdown("""
+            **Poem References**            
+            - [Poem Hunter](https://www.poemhunter.com)
+            - [Poem Generator](https://www.poem-generator.org.uk)
+            - [HelloPoetry](https://hellopoetry.com)
+            """)
+            
+    
+    submit_btn.click(
+        fn=predict_poem,
+        inputs=[text_input, model_selector],
+        outputs=[output_label]
+    )
+
+demo.launch()

best_model_deepseek_0.1_lstm.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63717f815fcfb8e27dfa853998fe031b2021467ecd547e459a4f26a09479a53
+size 119406080

best_model_hartmann_0.1_lstm.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:844122f8ba3616f2282e160663e5a671e1df2fbe1469a80a391bc5053e0daae5
+size 119993288

best_model_savani_0.1_lstm.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a3c6164ae322a44465c656c787b13313338f04d6d15e0c3ca8617368e6bd68
+size 119762684

custom_vocab.txt

@@ -0,0 +1,82 @@
+l
+mi
+e
+ultimo
+la
+per
+cor
+non
+viva
+lei
+mare
+rag
+ii
+b
+c
+d
+f
+g
+h
+j
+k
+m
+n
+o
+p
+q
+r
+s
+t
+u
+v
+w
+x
+y
+z
+st
+ye
+tr
+xxv
+ix
+iv
+iii
+vi
+vii
+viii
+xi
+xii
+xiii
+xv
+xvi
+xvii
+xviii
+xiv
+xvv
+ey
+hey
+oy
+yew
+of
+in
+the
+an
+a
+ami
+ah
+ih
+uh
+jest
+zest
+be
+rio
+they
+we
+i
+you
+she
+he
+it
+its
+is
+am
+are

gradio.ipynb

@@ -0,0 +1,355 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8d1ce753",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/hafizh/miniconda3/envs/MainCuda/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "2025-04-12 16:14:06.410469: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
+      "2025-04-12 16:14:06.423302: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
+      "E0000 00:00:1744449246.437801  116764 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "E0000 00:00:1744449246.442018  116764 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "W0000 00:00:1744449246.452843  116764 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
+      "W0000 00:00:1744449246.452871  116764 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
+      "W0000 00:00:1744449246.452873  116764 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
+      "W0000 00:00:1744449246.452874  116764 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
+      "2025-04-12 16:14:06.456742: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
+      "[nltk_data] Downloading package words to /home/hafizh/nltk_data...\n",
+      "[nltk_data]   Package words is already up-to-date!\n",
+      "[nltk_data] Downloading package punkt_tab to /home/hafizh/nltk_data...\n",
+      "[nltk_data]   Package punkt_tab is already up-to-date!\n",
+      "[nltk_data] Downloading package wordnet to /home/hafizh/nltk_data...\n",
+      "[nltk_data]   Package wordnet is already up-to-date!\n",
+      "[nltk_data] Downloading package stopwords to /home/hafizh/nltk_data...\n",
+      "[nltk_data]   Package stopwords is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "import tensorflow as tf\n",
+    "import pickle\n",
+    "import unicodedata\n",
+    "import contractions\n",
+    "import re\n",
+    "import nltk\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from nltk.corpus import stopwords, words\n",
+    "from nltk.stem import WordNetLemmatizer\n",
+    "from tensorflow.keras.models import load_model #type:ignore\n",
+    "from tensorflow.keras.utils import pad_sequences # type: ignore\n",
+    "\n",
+    "nltk.download('words')\n",
+    "nltk.download('punkt_tab')\n",
+    "nltk.download('wordnet')\n",
+    "nltk.download('stopwords') "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f037a836",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lemmatizer = WordNetLemmatizer()\n",
+    "stop_words = set(stopwords.words('english'))\n",
+    "english_words = set(words.words())\n",
+    "\n",
+    "def loadCustomDict(path):\n",
+    "    with open(path, 'r') as file:\n",
+    "        return set(line.strip().lower() for line in file if line.strip())\n",
+    "\n",
+    "def normalizeWhitespace(text):\n",
+    "    text = unicodedata.normalize('NFKC', text)\n",
+    "    text = contractions.fix(text)\n",
+    "    text = re.sub(r'[\\t\\r]+', ' ', text) # Menghapus tab\n",
+    "    text = re.sub(r'\\b\\d+\\b', '', text) # Menghilangkan angka\n",
+    "    text = re.sub(r'[-‐‑‒–—―]+', '', text)\n",
+    "    text = re.sub(r'[_﹍﹎＿]', '', text)\n",
+    "    text = re.sub(r'[^\\w\\s]', '', text) # Hilangkan symbol punctuation\n",
+    "    text = re.sub(r'\\b(\\w+)(?:\\s+\\1\\b)+', r'\\1', text)\n",
+    "    text = re.sub(r'\\s+', ' ', text).strip().lower()\n",
+    "    return text\n",
+    "\n",
+    "def removeOtherLanguage(text):\n",
+    "    phrase = ' translated'\n",
+    "    pos = text.find(phrase)\n",
+    "    if pos != -1:\n",
+    "        text = text[:pos].rstrip()\n",
+    "    text = re.sub(r'\\b\\w*[^\\x00-\\x7F]\\w*\\b', '', text)\n",
+    "    text = re.sub(r'\\s+', ' ', text).strip().lower()\n",
+    "    return text\n",
+    "\n",
+    "def removeNonEnglish(text_series, custom_dict):\n",
+    "    pattern = r'\\b(?:' + '|'.join(re.escape(word) for word in custom_dict) + r')\\b'\n",
+    "    temp_series = text_series.str.replace(pattern, '', case=False, regex=True)\n",
+    "    split_words = temp_series.str.split()\n",
+    "    exploded = split_words.explode()\n",
+    "    exploded = exploded[exploded.str.lower().isin(english_words)]\n",
+    "    filtered = exploded[~exploded.str.lower().isin(stop_words)]\n",
+    "    lemmatized = filtered.apply(lambda word: lemmatizer.lemmatize(word.lower()))\n",
+    "    cleaned_text_series = lemmatized.groupby(level=0).agg(' '.join)\n",
+    "    pattern2 = r'\\b(\\w+)(?:\\s+\\1\\b)+' #, r'\\1', text)\n",
+    "    ser = cleaned_text_series.reindex(text_series.index, fill_value='')\n",
+    "    text = ser.str.replace(pattern2, r'\\1', case=False, regex=True)\n",
+    "    return text\n",
+    "\n",
+    "def cleanInference(df):\n",
+    "    custom_dict = loadCustomDict('custom_vocab.txt')\n",
+    "    df['poem'] = df['poem'].apply(normalizeWhitespace)\n",
+    "    df['poem'] = df['poem'].apply(removeOtherLanguage)\n",
+    "    df['poem'] = removeNonEnglish(df['poem'], custom_dict)\n",
+    "    return df\n",
+    "\n",
+    "def kerasTokenizer(text, tokenizer):\n",
+    "    text_sequence = tokenizer.texts_to_sequences(text)\n",
+    "    text_padded = pad_sequences(text_sequence, maxlen=128)\n",
+    "    return text_padded\n",
+    "\n",
+    "def getLabelEncoder(name):\n",
+    "    hartmann = ['sadness', 'fear', 'anger', 'joy', 'neutral', 'surprise', 'disgust']\n",
+    "    savani = ['joy', 'sadness', 'anger', 'fear', 'love', 'surprise']\n",
+    "    deepseek = ['other', 'sadness', 'joy', 'hope', 'love']\n",
+    "    if name=='hartmann':\n",
+    "        return {i : label for i, label in enumerate(sorted(hartmann))}\n",
+    "    if name=='savani':\n",
+    "        return {i : label for i, label in enumerate(sorted(savani))}\n",
+    "    if name=='deepseek':\n",
+    "        return {i : label for i, label in enumerate(sorted(deepseek))}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "ffcb03a6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "poem1 = '''\n",
+    "Deliverance is not for me in renunciation.\n",
+    "I feel the embrace of freedom in a thousand bonds of delight.\n",
+    "\n",
+    "Thou ever pourest for me the fresh draught of thy wine of various\n",
+    "colours and fragrance, filling this earthen vessel to the brim.\n",
+    "\n",
+    "My world will light its hundred different lamps with thy flame\n",
+    "and place them before the altar of thy temple.\n",
+    "\n",
+    "No, I will never shut the doors of my senses.\n",
+    "The delights of sight and hearing and touch will bear thy delight.\n",
+    "\n",
+    "Yes, all my illusions will burn into illumination of joy,\n",
+    "and all my desires ripen into fruits of love.\n",
+    "'''"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2cedfa00",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "I0000 00:00:1744449252.416426  116764 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 5563 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Laptop GPU, pci bus id: 0000:01:00.0, compute capability: 8.9\n"
+     ]
+    }
+   ],
+   "source": [
+    "with open(f\"./tokenizer/tokenizer_savani_0.1_lstm.pkl\", \"rb\") as f:\n",
+    "    tokenizer_savani = pickle.load(f)\n",
+    "with open(f\"./tokenizer/tokenizer_hartmann_0.1_lstm.pkl\", \"rb\") as g:\n",
+    "    tokenizer_hartman = pickle.load(g)\n",
+    "with open(f\"./tokenizer/tokenizer_deepseek_0.1_lstm.pkl\", \"rb\") as h:\n",
+    "    tokenizer_deepseek = pickle.load(h)\n",
+    "\n",
+    "model_savani = load_model(f\"./model/best_model_savani_0.1_lstm.keras\")\n",
+    "model_hartman = load_model(f\"./model/best_model_hartmann_0.1_lstm.keras\")\n",
+    "model_deepseek = load_model(f\"./model/best_model_deepseek_0.1_lstm.keras\")\n",
+    "\n",
+    "MODELS = {\n",
+    "    \"savani\": {\n",
+    "        \"model\": model_savani,\n",
+    "        \"tokenizer\": tokenizer_savani\n",
+    "    },\n",
+    "    \"hartmann\": {\n",
+    "        \"model\": model_hartman,\n",
+    "        \"tokenizer\": tokenizer_hartman\n",
+    "    },\n",
+    "    \"deepseek\": {\n",
+    "        \"model\": model_deepseek,\n",
+    "        \"tokenizer\": tokenizer_deepseek\n",
+    "    },\n",
+    "}\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "1c9affe4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loaded_models = {}\n",
+    "\n",
+    "def load_model(model_name):\n",
+    "    if model_name not in loaded_models:\n",
+    "        tokenizer = MODELS[model_name]['tokenizer']\n",
+    "        model = MODELS[model_name]['model']\n",
+    "        loaded_models[model_name] = (tokenizer, model)\n",
+    "    return loaded_models[model_name]\n",
+    "    \n",
+    "\n",
+    "def predict_poem(poem, model_name):\n",
+    "    tokenizer, model = load_model(model_name)\n",
+    "    poem_df = pd.DataFrame({'poem' : [poem]})\n",
+    "    clean_poem_df = cleanInference(poem_df)\n",
+    "    text_keras = kerasTokenizer(clean_poem_df['poem'], tokenizer)\n",
+    "    result = model.predict(text_keras, verbose=0)\n",
+    "    predicted_labels = np.argmax(result, axis=1)\n",
+    "    dic = getLabelEncoder(model_name)\n",
+    "    return dic[predicted_labels[0]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4b844491",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "* Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Keyboard interruption in main thread... closing server.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with gr.Blocks(title=\"NLP Model Text Classifier\") as demo:\n",
+    "    gr.Markdown(\"## 📜 Poem Emotion Classification\")\n",
+    "    gr.Markdown(\"\"\"\n",
+    "    - **Step 1:** Select a labeling technique (model - each has different emotion labels)  \n",
+    "    - **Step 2:** Enter your poem text  \n",
+    "    - **Output:** Predicted emotion with confidence score  \n",
+    "    *Example: Try \"The sun shines bright\" with the Savani model*\n",
+    "    \"\"\")\n",
+    "    with gr.Row():\n",
+    "        with gr.Column():\n",
+    "            model_selector = gr.Dropdown(\n",
+    "                choices=list(MODELS.keys()),\n",
+    "                value=\"savani\",\n",
+    "                interactive=True,\n",
+    "                label=\"Select Labelling Technique Model\"\n",
+    "            )\n",
+    "            text_input = gr.Textbox(\n",
+    "                lines=5,\n",
+    "                placeholder=\"Enter text here...\",\n",
+    "                label=\"Input Text\",\n",
+    "                interactive=True\n",
+    "            )\n",
+    "            submit_btn = gr.Button(\"Classify\", variant=\"primary\")\n",
+    "        \n",
+    "        with gr.Column():\n",
+    "            output_label = gr.Label(label=\"Classification Results\")\n",
+    "            gr.Markdown(\"\"\"\n",
+    "            **Poem References**            \n",
+    "            - [Poem Hunter](https://www.poemhunter.com)\n",
+    "            - [Poem Generator](https://www.poem-generator.org.uk)\n",
+    "            - [HelloPoetry](https://hellopoetry.com)\n",
+    "            \"\"\")\n",
+    "            \n",
+    "    \n",
+    "    submit_btn.click(\n",
+    "        fn=predict_poem,\n",
+    "        inputs=[text_input, model_selector],\n",
+    "        outputs=[output_label]\n",
+    "    )\n",
+    "\n",
+    "demo.launch(debug=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b9868e38",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "MainCuda",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

requirements.txt

@@ -0,0 +1,7 @@
+tensorflow
+pickle
+unicodedata
+contractions
+nltk
+pandas
+numpy

tokenizer_deepseek_0.1_lstm.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5334fae5c4c2a533be4781c7ae70e36092daef2a9afe60bb6b0518a04bc581f
+size 1323687

tokenizer_hartmann_0.1_lstm.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95673c503bc2e483e49f070f4ca89ee5e63aa786c02bb83e0fbd6e208fd0d2f
+size 1330884

tokenizer_savani_0.1_lstm.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30daa553ad48943cfe255fee99482982c3fd1c99af36030dbe384219390e03d2
+size 1328993