bertopic-german-mails-small

This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.

Usage

To use this model, please install BERTopic:

pip install -U bertopic

You can use the model as follows:

from bertopic import BERTopic
topic_model = BERTopic.load("TheItCrOw/bertopic-german-mails-small")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 7
  • Number of training documents: 627
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 specificationsheet - der xsl - specs - xsl - parsen 40 Fehlermeldung "Fehler beim Parsen der XSL Daten" in der Gewinnkalkulation
0 mac - die installation - wenden sie sich - wenden sie - wenden 223 Interbase SPARQL Server - Installation fehlerhaft
1 auf den - sie bitte - die bestellnummer - anzeigen - stelle 137 Warehouses Prozessverwaltung und -übertragung
2 fuer - moechte - ueber - freundlichen gruessen - mit freundlichen gruessen 75 Softwareprobleme und Support
3 aktivierungscode - fehlerhaften - 27 - ticket - einer anderen 65 Softwarefehler bei Sales First Class
4 intel - core - ethernet - ghz - solarmobile 44 Hardwareprobleme bei der Installation von Sales First Class
5 build exception - build - project build exception - disc project build - project build 43 Brennvorgänge mit Build-Exception-Fehlern

Training hyperparameters

  • calculate_probabilities: True
  • language: None
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • nr_topics: None
  • seed_topic_list: None
  • top_n_words: 10
  • verbose: True
  • zeroshot_min_similarity: 0.7
  • zeroshot_topic_list: None

Framework versions

  • Numpy: 2.2.6
  • HDBSCAN: 0.8.40
  • UMAP: 0.5.9.post2
  • Pandas: 2.3.2
  • Scikit-Learn: 1.7.1
  • Sentence-transformers: 5.1.0
  • Transformers: 4.55.4
  • Numba: 0.61.2
  • Plotly: 6.3.0
  • Python: 3.12.0
Downloads last month
6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support