[E143] Labels for component 'tagger' not initialized on version 3.0.3

[HsengivS]

My Environment

• Operating System: Windows 10
• Python Version Used: 3.7.10
• spaCy Version Used: 3.0.3
• Environment Information:

Hi

I tried training a custom tagger, using the below command

python -m spacy train config.cfg --output ./output --paths.train ./train.spacy --paths.dev ./dev.spacy

I am getting the below error,

ℹ Using CPU

=========================== Initializing pipeline ===========================
Set up nlp object from config
Pipeline: ['transformer', 'tagger']
Created vocabulary
Finished initializing nlp object
Traceback (most recent call last):
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\runpy.py", line 85, in run_code
exec(code, run_globals)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\spacy_main.py", line 4, in
setup_cli()
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\spacy\cli_util.py", line 68, in setup_cli
command(prog_name=COMMAND)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\click\core.py", line 829, in call
return self.main(*args, **kwargs)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\click\core.py", line 782, in main
rv = self.invoke(ctx)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\click\core.py", line 1259, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\click\core.py", line 1066, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\click\core.py", line 610, in invoke
return callback(*args, **kwargs)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\typer\main.py", line 497, in wrapper
return callback(**use_params) # type: ignore
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\spacy\cli\train.py", line 56, in train_cli
nlp = init_nlp(config, use_gpu=use_gpu)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\spacy\training\initialize.py", line 70, in init_nlp
nlp.initialize(lambda: train_corpus(nlp), sgd=optimizer)
File "C:\Users\SMVP\Anaconda3\envs\spacy_v3_gpu\lib\site-packages\spacy\language.py", line 1246, in initialize
proc.initialize(get_examples, nlp=self, **p_settings)
File "spacy\pipeline\tagger.pyx", line 270, in spacy.pipeline.tagger.Tagger.initialize
File "spacy\pipeline\pipe.pyx", line 104, in spacy.pipeline.pipe.Pipe._require_labels
ValueError: [E143] Labels for component 'tagger' not initialized. This can be fixed by calling add_label, or by providing a representative batch of examples to the component's initialize method.

I can't find a way on how to add the custom labels.

Could anyone guide me on how this could be fixed...

Thanks in advance

[adrianeboyd]

The labels are normally read in from the docs train.spacy under token.tag_. Can you load the file and check that the docs are tagged?

import spacy
from spacy.tokens import DocBin

nlp = spacy.blank("en")
db = DocBin().from_disk("train.spacy")
for doc in db.get_docs(nlp.vocab):
    assert doc.has_annotation("TAG")
    # or just inspect the tags
    for token in doc:
        print(token.text, token.tag_)

[Tayaress51]

Hi !

I'm pretty new to NLP.
I got the same problem so I inspect the tags in my train data.
There is no tags but I don't know how to get them.

I'm trying to made my NER indentifie aircraft models. I first think problem came from the custom NER tag "aircraft".
Problem come from POS tags if I understand correctly.

In my mind, tags for tagger where present per default.
Actually, my training data are very few (I'm testing), so I foud strange to create my POS tags with them.
Will I use sample data like CoNLL before testing my training data ?

Please can you ligth my lantern ?
Thanks in advance.

[polm]

You shouldn't need to have POS tags in your training data in order to train an NER model. If you haven't done this before you might find it helpful to go through the spaCy course, which covers training an NER model.

If you'd like more help with this, please open a new thread and include your config file.

[Tayaress51]

OK thanks !
I will follow the course and open an new thread if I got problems