Sorry, The tokenizer model is not there. Have you can training a Spanish tokenizer using the universal dependency data? Daniel
> On Sep 13, 2018, at 12:03 PM, Dan Russ <[email protected]> wrote: > > Hello, > Have you tried the old 1.5 source forge models available at > http://opennlp.sourceforge.net/models-1.5/ > <http://opennlp.sourceforge.net/models-1.5/> ? The Spanish models start > with es-. > Daniel > > > >> On Sep 13, 2018, at 5:03 AM, Elsa Cerezo Fernández <[email protected] >> <mailto:[email protected]>> wrote: >> >> Hello, >> >> >> >> I do not know if you can help me: >> >> >> >> I am using the OpenNLP library v1.8.4 as a NuGet in VisualStudio and the >> only Spanish models I have found are from previous versions of the library. >> Even so, I have used them and they do not work for me, it fails to >> initialize the TokenizerModel object. I have used the model in English v1.5 >> and if it works correctly. >> >> >> >> If there are no Spanish models available, could you tell me how to create >> one? I have seen that .train files are used with data for the training but >> I do not know the structure that they should have or anything. >> >> >> >> Thanks in advance! >> >> >> >> E. Cerezo >
