Christian Kasim Loan

Hi @filemon11 this looks like Spark is not properly setup on Windows, can you make sure you follow all steps involved to install spark-nlp and pyspark for windows? The windows...

Hi @GladiatorX , thank you for sharing this, looks like the spell is mapping to an outdated model. this will be fixed soon,

Hi @m3r3lin NLU is dropping the elmo embeddings you need to set `nlu.load('elmo').predict('Hello world', get_embeddings=True)` Let me know if you encounter any other issues :)

Hi @krico1 large embeddings like biobert can be quite slow because of the large deep learning models used for it. But you can also achieve ~ 10x speedup by using...

Hi @sam-abens yes NLU can run in any environment, can you share what operating system you are running? You need to have Java8 installed on your machine and make sure...

Thank you @jonnyzwifor this issue, this is indeed a bug with the way NLU generates NLP pipelines and we are looking into fixing this

Hi yes exactly thanks for answering the questions @ahmedlone127

Hi @d0tN3t could you specify the Java-version you have installed? You need Java 8 for NLU

HI @gromajus currently there is no straightforward way to mute the Spark Logging messages. We are looking into this and hopefully can provide a solution soon.

Hi @atoutou ```python pipe = nlu.load('xx.embed_sentence.labse', gpu=True) pipe.print_info() ``` will print ``` The following parameters are configurable for this NLU pipeline (You can copy paste the examples) : >>> pipe['bert_sentence@labse']...