Commit message

app.py

@@ -0,0 +1,19 @@
+from flask import Flask, render_template, request, jsonify
+from chat import get_response
+
+app = Flask(__name__)
+
+@app.get("/")
+def index_get():
+    return render_template("base.html")
+
+@app.post("/predict")
+def predict():
+    text = request.get_json().get("message")
+    response = get_response(text)
+    message = {"answer": response}
+    return jsonify(message)
+
+
+if __name__ == "__main__":
+    app.run(debug=True)

chat.py

@@ -0,0 +1,84 @@
+import random
+import json
+
+import torch
+
+from model import NeuralNet
+from nltk_utils import bag_of_words, tokenize
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+with open('intents.json', 'r') as json_data:
+    intents = json.load(json_data)
+
+FILE = 'data.pth'
+data = torch.load(FILE)
+
+input_size = data["input_size"]
+hidden_size = data["hidden_size"]
+output_size = data["output_size"]
+all_words = data["all_words"]
+tags = data["tags"]
+model_state = data["model_state"]
+
+model = NeuralNet(input_size,hidden_size,output_size).to(device)
+model.load_state_dict(model_state)
+model.eval()
+
+bot_name = "Anis"
+# print("Let's chat! (type 'quit' to exit)")
+# while True:
+#     sentence = input("You: ")
+#     if sentence == "quit":
+#         break
+
+#     sentence = tokenize(sentence)
+#     X = bag_of_words(sentence, all_words)
+#     X = X.reshape(1, X.shape[0])
+#     X = torch.from_numpy(X).to(device)
+
+#     output = model(X)
+#     _, predicted = torch.max(output, dim=1)
+
+#     tag = tags[predicted.item()]
+
+#     probs = torch.softmax(output, dim=1)
+#     prob = probs[0][predicted.item()]
+#     if prob.item() > 0.75:
+#         for intent in intents['intents']:
+#             if tag == intent['tag']:
+#                 print(f"{bot_name}: { random.choice(intent['responses'])}")
+#     else:
+#         print(f"{bot_name}: I do not understand...")
+
+def get_response(msg):
+    sentence = tokenize(msg)
+    X = bag_of_words(sentence, all_words)
+    X = X.reshape(1, X.shape[0])
+    X = torch.from_numpy(X).to(device)
+
+    output = model(X)
+    _, predicted = torch.max(output, dim=1)
+
+    tag = tags[predicted.item()]
+
+    probs = torch.softmax(output, dim=1)
+    prob = probs[0][predicted.item()]
+    if prob.item() > 0.75:
+        for intent in intents['intents']:
+            if tag == intent["tag"]:
+                return random.choice(intent['responses'])
+    
+    return "I do not understand..."
+
+
+if __name__ == "__main__":
+    print("Let's chat! (type 'quit' to exit)")
+    while True:
+        # sentence = "do you use credit cards?"
+        sentence = input("You: ")
+        if sentence == "quit":
+            break
+
+        resp = get_response(sentence)
+        print(resp)

data.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e72a22849441369c25180e1ca209ce65e2921c2aea6d01a9c6c06cf50e6004bd
+size 5290

intents.json

@@ -0,0 +1,102 @@
+{
+  "intents": [
+    {
+      "tag": "greeting",
+      "patterns": [
+        "Hi",
+        "Hello",
+        "Hey",
+        "Hi there"
+      ],
+      "responses": [
+        "Hello! How can I help you today?",
+        "Hi there! What can I do for you?"
+      ]
+    },
+    {
+      "tag": "product_inquiry",
+      "patterns": [
+        "Can you tell me about your products?",
+        "What products do you sell?",
+        "Tell me about your products"
+      ],
+      "responses": [
+        "We offer a variety of products. Please visit our website for more details.",
+        "You can find all our products listed on our website."
+      ]
+    },
+    {
+      "tag": "order_status",
+      "patterns": [
+        "Where is my order?",
+        "Can you check my order status?",
+        "I want to know my order status"
+      ],
+      "responses": [
+        "Please provide your order number, and I will check the status for you.",
+        "Let me know your order number to check the status."
+      ]
+    },
+    {
+      "tag": "return_policy",
+      "patterns": [
+        "What is your return policy?",
+        "How do I return a product?",
+        "Can I return a product?"
+      ],
+      "responses": [
+        "You can return products within 30 days of purchase. Visit our website for more details.",
+        "Our return policy allows returns within 30 days. Please check our website for the process."
+      ]
+    },
+    {
+      "tag": "shipping_info",
+      "patterns": [
+        "How long does shipping take?",
+        "What are your shipping options?",
+        "Tell me about your shipping"
+      ],
+      "responses": [
+        "Shipping usually takes 3-5 business days. We also offer express shipping.",
+        "Standard shipping takes 3-5 days. Express shipping is also available."
+      ]
+    },
+    {
+      "tag": "contact_support",
+      "patterns": [
+        "How do I contact support?",
+        "I need help from customer support",
+        "Can you give me your support contact?"
+      ],
+      "responses": [
+        "You can contact our support team at support@mail.com or call +123456789.",
+        "Reach out to our support team via email at support@mail.com or phone at +123456789."
+      ]
+    },
+    {
+      "tag": "business_hours",
+      "patterns": [
+        "What are your business hours?",
+        "When are you open?",
+        "Tell me your working hours"
+      ],
+      "responses": [
+        "Our business hours are Monday to Friday, 9 AM to 5 PM.",
+        "We are open from Monday to Friday, 9 AM to 5 PM."
+      ]
+    },
+    {
+      "tag": "goodbye",
+      "patterns": [
+        "Bye",
+        "Goodbye",
+        "Thanks for your help"
+      ],
+      "responses": [
+        "Goodbye! Have a great day!",
+        "You're welcome! Bye!"
+      ]
+    }
+  ]
+}
+

model.py

@@ -0,0 +1,19 @@
+import torch
+import torch.nn as nn
+
+class NeuralNet(nn.Module):
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(NeuralNet, self).__init__()
+        self.l1 = nn.Linear(input_size, hidden_size)
+        self.l2 = nn.Linear(hidden_size, hidden_size)
+        self.l3 = nn.Linear(hidden_size, num_classes)
+        self.relu = nn.ReLU()
+
+    def forward(self, x):
+        out = self.l1(x)
+        out = self.relu(out)
+        out = self.l2(out)
+        out = self.relu(out)
+        out = self.l3(out)
+
+        return out

nltk_data/tokenizers/punkt.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c3078994aeaf650bfc8e028be4fb42b4a0d177d41c012b6a983979653660ec
+size 13905355

nltk_data/tokenizers/punkt/PY3/README

@@ -0,0 +1,98 @@
+Pretrained Punkt Models -- Jan Strunk (New version trained after issues 313 and 514 had been corrected)
+
+Most models were prepared using the test corpora from Kiss and Strunk (2006). Additional models have
+been contributed by various people using NLTK for sentence boundary detection.
+
+For information about how to use these models, please confer the tokenization HOWTO:
+http://nltk.googlecode.com/svn/trunk/doc/howto/tokenize.html
+and chapter 3.8 of the NLTK book:
+http://nltk.googlecode.com/svn/trunk/doc/book/ch03.html#sec-segmentation
+
+There are pretrained tokenizers for the following languages:
+
+File                Language            Source                             Contents                Size of training corpus(in tokens)           Model contributed by
+=======================================================================================================================================================================
+czech.pickle        Czech               Multilingual Corpus 1 (ECI)        Lidove Noviny                   ~345,000                             Jan Strunk / Tibor Kiss
+                                                                           Literarni Noviny
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+danish.pickle       Danish              Avisdata CD-Rom Ver. 1.1. 1995     Berlingske Tidende              ~550,000                             Jan Strunk / Tibor Kiss
+                                        (Berlingske Avisdata, Copenhagen)  Weekend Avisen
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+dutch.pickle        Dutch               Multilingual Corpus 1 (ECI)        De Limburger                    ~340,000                             Jan Strunk / Tibor Kiss
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+english.pickle      English             Penn Treebank (LDC)                Wall Street Journal             ~469,000                             Jan Strunk / Tibor Kiss
+                    (American)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+estonian.pickle     Estonian            University of Tartu, Estonia       Eesti Ekspress                  ~359,000                             Jan Strunk / Tibor Kiss
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+finnish.pickle      Finnish             Finnish Parole Corpus, Finnish     Books and major national        ~364,000                             Jan Strunk / Tibor Kiss
+                                        Text Bank (Suomen Kielen           newspapers
+                                        Tekstipankki)
+                                        Finnish Center for IT Science
+                                        (CSC)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+french.pickle       French              Multilingual Corpus 1 (ECI)        Le Monde                        ~370,000                             Jan Strunk / Tibor Kiss
+                    (European)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+german.pickle       German              Neue Zürcher Zeitung AG            Neue Zürcher Zeitung            ~847,000                             Jan Strunk / Tibor Kiss
+                    (Switzerland)       CD-ROM
+                    (Uses "ss"
+                     instead of "ß")
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+greek.pickle        Greek               Efstathios Stamatatos              To Vima (TO BHMA)               ~227,000                             Jan Strunk / Tibor Kiss
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+italian.pickle      Italian             Multilingual Corpus 1 (ECI)        La Stampa, Il Mattino           ~312,000                             Jan Strunk / Tibor Kiss
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+norwegian.pickle    Norwegian           Centre for Humanities              Bergens Tidende                 ~479,000                             Jan Strunk / Tibor Kiss
+                    (Bokmål and         Information Technologies,
+                     Nynorsk)           Bergen
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+polish.pickle       Polish              Polish National Corpus             Literature, newspapers, etc.  ~1,000,000                             Krzysztof Langner
+                                        (http://www.nkjp.pl/)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+portuguese.pickle   Portuguese          CETENFolha Corpus                  Folha de São Paulo              ~321,000                             Jan Strunk / Tibor Kiss
+                    (Brazilian)         (Linguateca)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+slovene.pickle      Slovene             TRACTOR                            Delo                            ~354,000                             Jan Strunk / Tibor Kiss
+                                        Slovene Academy for Arts
+                                        and Sciences
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+spanish.pickle      Spanish             Multilingual Corpus 1 (ECI)        Sur                             ~353,000                             Jan Strunk / Tibor Kiss
+                    (European)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+swedish.pickle      Swedish             Multilingual Corpus 1 (ECI)        Dagens Nyheter                  ~339,000                             Jan Strunk / Tibor Kiss
+                                                                           (and some other texts)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+turkish.pickle      Turkish             METU Turkish Corpus                Milliyet                        ~333,000                             Jan Strunk / Tibor Kiss
+                                        (Türkçe Derlem Projesi)
+                                        University of Ankara
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+The corpora contained about 400,000 tokens on average and mostly consisted of newspaper text converted to
+Unicode using the codecs module.
+
+Kiss, Tibor and Strunk, Jan (2006): Unsupervised Multilingual Sentence Boundary Detection.
+Computational Linguistics 32: 485-525.
+
+---- Training Code ----
+
+# import punkt
+import nltk.tokenize.punkt
+
+# Make a new Tokenizer
+tokenizer = nltk.tokenize.punkt.PunktSentenceTokenizer()
+
+# Read in training corpus (one example: Slovene)
+import codecs
+text = codecs.open("slovene.plain","Ur","iso-8859-2").read()
+
+# Train tokenizer
+tokenizer.train(text)
+
+# Dump pickled tokenizer
+import pickle
+out = open("slovene.pickle","wb")
+pickle.dump(tokenizer, out)
+out.close()
+
+---------

nltk_data/tokenizers/punkt/PY3/czech.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b0734b6fbe8e8d7cac79f48d1dd9f853824e57c4e3594dadd74ba2c1d97f50
+size 1119050

nltk_data/tokenizers/punkt/PY3/danish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6189c7dd254e29e2bd406a7f6a4336297c8953214792466a790ea4444223ceb3
+size 1191710

nltk_data/tokenizers/punkt/PY3/dutch.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda0d6a13f02e8898daec7fe923da88e25abe081bcfa755c0e015075c215fe4c
+size 693759

nltk_data/tokenizers/punkt/PY3/english.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cad3758596392364e3be9803dbd7ebeda384b68937b488a01365f5551bb942c
+size 406697

nltk_data/tokenizers/punkt/PY3/estonian.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b364f72538d17b146a98009ad239a8096ce6c0a8b02958c0bc776ecd0c58a25f
+size 1499502

nltk_data/tokenizers/punkt/PY3/finnish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4b5ff5500ee851c456f9dd40d5fc0d8c1859c88eb3178de1317d26b7d22833
+size 1852226

nltk_data/tokenizers/punkt/PY3/french.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e3a4cd2971989b3cb9fd3433a6f15d17981e464db2be039364313b5de94f29
+size 553575

nltk_data/tokenizers/punkt/PY3/german.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcbbe85e2042a019b1a6e37fd8c153286c38ba201fae0f5bfd9a3f74abae25c
+size 1463575

nltk_data/tokenizers/punkt/PY3/greek.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85dabc44ab90a5f208ef37ff6b4892ebe7e740f71fb4da47cfd95417ca3e22fd
+size 876006

nltk_data/tokenizers/punkt/PY3/italian.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a94007b1e4ffdc4d1a190185ca5442c3dafeb17ab39d30329e84cd74a43947
+size 615089

nltk_data/tokenizers/punkt/PY3/malayalam.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8cf58acbdb7f472ac40affc13663be42dafb47c15030c11ade0444c9e0e53d
+size 221207

nltk_data/tokenizers/punkt/PY3/norwegian.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff7a46d1438b311457d15d7763060b8d3270852c1850fd788c5cee194dc4a1d
+size 1181271

nltk_data/tokenizers/punkt/PY3/polish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624900ae3ddfb4854a98c5d3b8b1c9bb719975f33fee61ce1441dab9f8a00718
+size 1738386

nltk_data/tokenizers/punkt/PY3/portuguese.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a0b7b25c3c7471e1791b66a31bbb530afbb0160aee4fcecf0107652067b4a1
+size 611919

nltk_data/tokenizers/punkt/PY3/russian.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549762f8190024d89b511472df21a3a135eee5d9233e63ac244db737c2c61d7e
+size 33020

nltk_data/tokenizers/punkt/PY3/slovene.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ef2cc0ed27d79b3aa635cbbc40ad811883a75a4b8a8be1ae406972870fd864
+size 734444

nltk_data/tokenizers/punkt/PY3/spanish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164a50fadc5a49f8ec7426eae11d3111ee752b48a3ef373d47745011192a5984
+size 562337

nltk_data/tokenizers/punkt/PY3/swedish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f7d538bfd5266633b09e842cd92e9e0ac10f1d923bf211e1497972ddc47318
+size 979681

nltk_data/tokenizers/punkt/PY3/turkish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae68ef5863728ac5332e87eb1f6bae772ff32a13a4caa2b01a5c68103e853c5b
+size 1017038

nltk_data/tokenizers/punkt/README

@@ -0,0 +1,98 @@
+Pretrained Punkt Models -- Jan Strunk (New version trained after issues 313 and 514 had been corrected)
+
+Most models were prepared using the test corpora from Kiss and Strunk (2006). Additional models have
+been contributed by various people using NLTK for sentence boundary detection.
+
+For information about how to use these models, please confer the tokenization HOWTO:
+http://nltk.googlecode.com/svn/trunk/doc/howto/tokenize.html
+and chapter 3.8 of the NLTK book:
+http://nltk.googlecode.com/svn/trunk/doc/book/ch03.html#sec-segmentation
+
+There are pretrained tokenizers for the following languages:
+
+File                Language            Source                             Contents                Size of training corpus(in tokens)           Model contributed by
+=======================================================================================================================================================================
+czech.pickle        Czech               Multilingual Corpus 1 (ECI)        Lidove Noviny                   ~345,000                             Jan Strunk / Tibor Kiss
+                                                                           Literarni Noviny
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+danish.pickle       Danish              Avisdata CD-Rom Ver. 1.1. 1995     Berlingske Tidende              ~550,000                             Jan Strunk / Tibor Kiss
+                                        (Berlingske Avisdata, Copenhagen)  Weekend Avisen
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+dutch.pickle        Dutch               Multilingual Corpus 1 (ECI)        De Limburger                    ~340,000                             Jan Strunk / Tibor Kiss
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+english.pickle      English             Penn Treebank (LDC)                Wall Street Journal             ~469,000                             Jan Strunk / Tibor Kiss
+                    (American)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+estonian.pickle     Estonian            University of Tartu, Estonia       Eesti Ekspress                  ~359,000                             Jan Strunk / Tibor Kiss
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+finnish.pickle      Finnish             Finnish Parole Corpus, Finnish     Books and major national        ~364,000                             Jan Strunk / Tibor Kiss
+                                        Text Bank (Suomen Kielen           newspapers
+                                        Tekstipankki)
+                                        Finnish Center for IT Science
+                                        (CSC)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+french.pickle       French              Multilingual Corpus 1 (ECI)        Le Monde                        ~370,000                             Jan Strunk / Tibor Kiss
+                    (European)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+german.pickle       German              Neue Zürcher Zeitung AG            Neue Zürcher Zeitung            ~847,000                             Jan Strunk / Tibor Kiss
+                    (Switzerland)       CD-ROM
+                    (Uses "ss"
+                     instead of "ß")
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+greek.pickle        Greek               Efstathios Stamatatos              To Vima (TO BHMA)               ~227,000                             Jan Strunk / Tibor Kiss
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+italian.pickle      Italian             Multilingual Corpus 1 (ECI)        La Stampa, Il Mattino           ~312,000                             Jan Strunk / Tibor Kiss
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+norwegian.pickle    Norwegian           Centre for Humanities              Bergens Tidende                 ~479,000                             Jan Strunk / Tibor Kiss
+                    (Bokmål and         Information Technologies,
+                     Nynorsk)           Bergen
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+polish.pickle       Polish              Polish National Corpus             Literature, newspapers, etc.  ~1,000,000                             Krzysztof Langner
+                                        (http://www.nkjp.pl/)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+portuguese.pickle   Portuguese          CETENFolha Corpus                  Folha de São Paulo              ~321,000                             Jan Strunk / Tibor Kiss
+                    (Brazilian)         (Linguateca)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+slovene.pickle      Slovene             TRACTOR                            Delo                            ~354,000                             Jan Strunk / Tibor Kiss
+                                        Slovene Academy for Arts
+                                        and Sciences
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+spanish.pickle      Spanish             Multilingual Corpus 1 (ECI)        Sur                             ~353,000                             Jan Strunk / Tibor Kiss
+                    (European)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+swedish.pickle      Swedish             Multilingual Corpus 1 (ECI)        Dagens Nyheter                  ~339,000                             Jan Strunk / Tibor Kiss
+                                                                           (and some other texts)
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+turkish.pickle      Turkish             METU Turkish Corpus                Milliyet                        ~333,000                             Jan Strunk / Tibor Kiss
+                                        (Türkçe Derlem Projesi)
+                                        University of Ankara
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+The corpora contained about 400,000 tokens on average and mostly consisted of newspaper text converted to
+Unicode using the codecs module.
+
+Kiss, Tibor and Strunk, Jan (2006): Unsupervised Multilingual Sentence Boundary Detection.
+Computational Linguistics 32: 485-525.
+
+---- Training Code ----
+
+# import punkt
+import nltk.tokenize.punkt
+
+# Make a new Tokenizer
+tokenizer = nltk.tokenize.punkt.PunktSentenceTokenizer()
+
+# Read in training corpus (one example: Slovene)
+import codecs
+text = codecs.open("slovene.plain","Ur","iso-8859-2").read()
+
+# Train tokenizer
+tokenizer.train(text)
+
+# Dump pickled tokenizer
+import pickle
+out = open("slovene.pickle","wb")
+pickle.dump(tokenizer, out)
+out.close()
+
+---------

nltk_data/tokenizers/punkt/czech.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba73d293c7d7953956bcf02f3695ec5c1f0d527f2a3c38097f5593394fa1690
+size 1265552

nltk_data/tokenizers/punkt/danish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea29760a0a9197f52ca59e78aeafc5a6f55d05258faf7db1709b2b9eb321ef20
+size 1264725

nltk_data/tokenizers/punkt/dutch.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8e26b3d68c45c38e594d19e2d5677447bfdcaa636d3b1e7acfed0e9272d73c
+size 742624

nltk_data/tokenizers/punkt/english.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda37972ae88998a6fd3e3ec002697a6bd362b32d050fda7d7ca5276873092aa
+size 433305

nltk_data/tokenizers/punkt/estonian.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3867fee26a36bdb197c64362aa13ac683f5f33fa4d0d225a5d56707582a55a1d
+size 1596714

nltk_data/tokenizers/punkt/finnish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9e17b3d5b4df76345d812b8a65b1da0767eda5086eadcc11e625eef0942835
+size 1951656

nltk_data/tokenizers/punkt/french.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de05f3d5647d3d2296626fb83f68428e4c6ad6e05a00ed4694c8bdc8f2f197ee
+size 583482

nltk_data/tokenizers/punkt/german.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab497fa085413130c8fd0fb13b929128930afe2f6a26ea8715c95df7088e97c
+size 1526714

nltk_data/tokenizers/punkt/greek.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21752a6762fad5cfe46fb5c45fad9a85484a0e8e81c67e6af6fb973cfc27d67c
+size 1953106

nltk_data/tokenizers/punkt/italian.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb2717d7be5f26e860a92e05acf69b1123a5f4527cd7a269a9ab9e9e668c805
+size 658331

nltk_data/tokenizers/punkt/malayalam.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8cf58acbdb7f472ac40affc13663be42dafb47c15030c11ade0444c9e0e53d
+size 221207

nltk_data/tokenizers/punkt/norwegian.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a97f8f9a03a0338dd746bcc89a0ae0f54ae43b835fa37d83e279e1ca794faf
+size 1259779

nltk_data/tokenizers/punkt/polish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16127b6d10933427a3e90fb20e9be53e1fb371ff79a730c1030734ed80b90c92
+size 2042451

nltk_data/tokenizers/punkt/portuguese.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb01bf7c79a4eadc2178bbd209665139a0e4b38f2d1c44fef097de93955140e0
+size 649051

nltk_data/tokenizers/punkt/russian.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc984432fbe31f7000014f8047502476889169c60f09be5413ca09276b16c909
+size 33027

nltk_data/tokenizers/punkt/slovene.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dac650212b3787b39996c01bd2084115493e6f6ec390bab61f767525b08b8ea
+size 832867

nltk_data/tokenizers/punkt/spanish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271dc6027c4aae056f72a9bfab5645cf67e198bf4f972895844e40f5989ccdc3
+size 597831

nltk_data/tokenizers/punkt/swedish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d50ebdad6caa87715f2e300b1217ec92c42de205a543cc4a56903bd2c9acfa
+size 1034496

nltk_data/tokenizers/punkt/turkish.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ae47d76501d027698809d12e75292c9c392910488543342802f95db9765ccc
+size 1225013