Maiia Guseva

sentence_model = SentenceTransformer("paraphrase-multilingual-mpnet-base-v2") hdbscan_model = HDBSCAN(min_cluster_size=200, metric='euclidean', cluster_selection_method='eom', prediction_data=True, min_samples=3) umap_model = UMAP(n_neighbors=15, n_components=10, metric='cosine', low_memory=False, random_state=17) topic_model = BERTopic(embedding_model=sentence_model, diversity=0.3, hdbscan_model=hdbscan_model, umap_model=umap_model, top_n_words=30, nr_topics="auto", verbose=True,) topics, probs = topic_model.fit_transform(titles)...