Create app.py

app.py

@@ -0,0 +1,82 @@
+import nltk
+nltk.download('punkt')
+nltk.download('stopwords')
+
+# Fonction summarize
+def summarizer_FS(Text):
+  # Tokeniser article_text en phrase
+  sentences_list = nltk.sent_tokenize(Text)
+  # Stopwords
+  stopwords = nltk.corpus.stopwords.words('english')
+  # Dictionnaire de fréquences des mots
+  word_frequencies = {}
+  # calculer les fréquences des mots
+  for word in nltk.word_tokenize(Text):
+    if word not in stopwords:
+      if word not in word_frequencies.keys():
+        word_frequencies[word] = 1
+      else:
+        word_frequencies[word] += 1
+  # Fréquence maximale de word_frequencies
+  freq_maximum =max(word_frequencies.values())
+  # Calculer la fréquence pondérée de chaque mot
+  for word in word_frequencies.keys():
+    word_frequencies[word] =  word_frequencies[word]/freq_maximum
+  # Liste des scores de chaque phrase
+  sentence_scores = {}
+  # Calculer le score de chaque phrase
+  for sent in sentences_list:
+    for word in nltk.word_tokenize(sent.lower()):
+      if word in word_frequencies.keys():
+        # if len(sent.split(' ')) < 30:
+          if sent not in sentence_scores.keys():
+            sentence_scores[sent]= word_frequencies[word]
+          else:
+            sentence_scores[sent] +=word_frequencies[word]
+  # Ordonner les phrases par pondération et recupérer les 10 premières phrases
+  summary_sentences = sorted(sentence_scores, key = sentence_scores.get, reverse = True)[:5]
+  # regrouper ensemble les phrases qui ont les poids les plus élévés
+  summary = ' '.join(summary_sentences)
+
+  return summary
+
+# Importer pipeline
+from transformers import pipeline
+# Modèle de summarization
+summarizer = pipeline(task="summarization",
+                      model="facebook/bart-large-cnn")
+
+# Définir une fonction summarize_t
+def summarizer_t(input):
+    output = summarizer(input)
+    return output[0]['summary_text']
+
+
+# Déployer
+import gradio as gr
+import os
+# Création de blocks
+demo = gr.Blocks()
+
+summarizer1 = gr.Interface(fn=summarizer_FS,
+                    inputs=[gr.Textbox(label="Text to summarize", lines=6)],
+                    outputs=[gr.Textbox(label="Result", lines=3)],
+                    title="Text summarization with NLTK",
+                    description="Summarize any text from scracth under the hood!"
+                   )
+summarizer2 = gr.Interface(fn=summarizer_t,
+                    inputs=[gr.Textbox(label="Text to summarize", lines=6)],
+                    outputs=[gr.Textbox(label="Result", lines=3)],
+                    title="Text summarization with bart-large-cnn ",
+                    description="Summarize any text using facebook/bart-large-cnn model under the hood!"
+                   )
+
+with demo:
+    gr.TabbedInterface(
+        [summarizer1,
+         summarizer2],
+        ["Summarize from scrath",
+         "Summarize using bart"],
+    )
+
+demo.launch()