first vers files

app.py

@@ -0,0 +1,43 @@
+from gensim.models.keyedvectors import KeyedVectors
+import pickle
+from nltk.tokenize import word_tokenize
+import gradio as gr
+
+
+# Use gensim Keyvectors to read the embbedings 
+wordvectors_file_vec = 'smaller_model_spa.txt'
+smaller_model = KeyedVectors.load_word2vec_format(wordvectors_file_vec)
+with open('stop_words.pkl', 'rb') as f:
+    stop_words = pickle.load(f)
+
+
+def filter_words(x):
+    word_tokens = word_tokenize(x)
+    filtered_sentence = [w for w in word_tokens if not w.lower() in stop_words]
+    return filtered_sentence
+
+def reverse_dictionary(definicion):
+    words = filter_words(definicion)
+    list_similar = smaller_model.most_similar_cosmul(positive= words)
+    return list_to_html(list_similar)
+
+def list_to_html(lst, title="Results"):
+    html_str = f"<h3>{title}</h3><ul>"
+    for word, score in lst:
+        html_str += f"<li><b>{word}</b>: {score:.2f}</li>"
+    html_str += "</ul>"
+    return html_str
+
+
+title = "Diccionario inverso en español"
+description = "Un diccionario inverso utilizando embeddings Word2Vec de SBWCA y filtrando palabras de Wikcionario. Creado como demo para Gradio y HuggingFace Spaces."
+examples = ['angustia porque se te olvido algo']
+
+
+gr.Interface(fn = reverse_dictionary, 
+             inputs = gr.inputs.Textbox(lines=5, placeholder="Enter your text here..."), 
+             outputs= gr.outputs.HTML(),
+             title = title,
+             description = description,
+             examples = examples).launch(share=True)
+

requirements.txt

@@ -0,0 +1,2 @@
+gensim
+nltk

smaller_model_spa.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bfe210640107736d63109016e474d178f7bce196c0bec951a3abad7c83913a
+size 491155883

stop_words.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60132a636523571f9be86856ab0ce292e842cda456d1dfebb81c8997ef156775
+size 2818