• Supports 30 languages (20 languages supported by previous versions). Including Powershell and Batch #2
• Robust and scalable training workflow, using Tensorflow dataset API https://www.tensorflow.org/api_docs/python/tf/data/Dataset
• Way simpler yet as performant feature engineering
• More concise documentation
• Simple check on detection probabilities to avoid classifying plain text as source code #16 #15
• Exposes the detection probabilities with guess.probabilities(source_code) method. #14
• Updated Tensorflow to the latest version 2.2.0 #12
• Use up to date Tensorflow canned classifier #9
• guess.language_name(source_code) now identifies empty content #6
• Guesslang dataset creation moved to a new dedicated repository https://github.com/yoeo/guesslangtools #5