mirror of
https://github.com/explosion/spaCy.git
synced 2025-05-02 23:03:41 +03:00
Add all strings from source models (#6736)
Add all strings from the source model when adding a pipe from a source model. Minor: * Skip `disable=["vocab", "tokenizer"]` when loading a source model from the config, since this doesn't do anything and is misleading.
This commit is contained in:
parent
9328dd5625
commit
c8b4370865
|
@ -697,6 +697,8 @@ class Language:
|
||||||
source_config = source.config.interpolate()
|
source_config = source.config.interpolate()
|
||||||
pipe_config = util.copy_config(source_config["components"][source_name])
|
pipe_config = util.copy_config(source_config["components"][source_name])
|
||||||
self._pipe_configs[name] = pipe_config
|
self._pipe_configs[name] = pipe_config
|
||||||
|
for s in source.vocab.strings:
|
||||||
|
self.vocab.strings.add(s)
|
||||||
return pipe, pipe_config["factory"]
|
return pipe, pipe_config["factory"]
|
||||||
|
|
||||||
def add_pipe(
|
def add_pipe(
|
||||||
|
@ -1619,9 +1621,7 @@ class Language:
|
||||||
if model not in source_nlps:
|
if model not in source_nlps:
|
||||||
# We only need the components here and we need to init
|
# We only need the components here and we need to init
|
||||||
# model with the same vocab as the current nlp object
|
# model with the same vocab as the current nlp object
|
||||||
source_nlps[model] = util.load_model(
|
source_nlps[model] = util.load_model(model, vocab=nlp.vocab)
|
||||||
model, vocab=nlp.vocab, disable=["vocab", "tokenizer"]
|
|
||||||
)
|
|
||||||
source_name = pipe_cfg.get("component", pipe_name)
|
source_name = pipe_cfg.get("component", pipe_name)
|
||||||
nlp.add_pipe(source_name, source=source_nlps[model], name=pipe_name)
|
nlp.add_pipe(source_name, source=source_nlps[model], name=pipe_name)
|
||||||
disabled_pipes = [*config["nlp"]["disabled"], *disable]
|
disabled_pipes = [*config["nlp"]["disabled"], *disable]
|
||||||
|
|
Loading…
Reference in New Issue
Block a user