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
> 

Reply via email to