Skip to content

edited engine name and add phayathai pos_tag model to transformer_tag #871

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

edited engine name and add phayathai pos_tag model to transformer_tag #871

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a3063e9
edited engine name and add phayathai pos_tag model to transformer_tag
MpolaarbearM Nov 30, 2023
b01c1e3
edit pep8 suggestion
MpolaarbearM Nov 30, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 12 additions & 7 deletions pythainlp/tag/pos_tag.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,12 +180,13 @@ def pos_tag_sents(


def pos_tag_transformers(
words: str, engine: str = "bert-base-th-cased-blackboard"
words: str, engine: str = "phayathai"
):
"""
"wangchanberta-ud-thai-pud-upos",
"mdeberta-v3-ud-thai-pud-upos",
"bert-base-th-cased-blackboard",
"wangchanberta",
"mdeberta",
"bert_cased",
"phayathai",

"""

Expand All @@ -199,17 +200,21 @@ def pos_tag_transformers(
if not words:
return []

if engine == "wangchanberta-ud-thai-pud-upos":
if engine == "wangchanberta":
model = AutoModelForTokenClassification.from_pretrained(
"Pavarissy/wangchanberta-ud-thai-pud-upos")
tokenizer = AutoTokenizer.from_pretrained("Pavarissy/wangchanberta-ud-thai-pud-upos")
elif engine == "mdeberta-v3-ud-thai-pud-upos":
elif engine == "mdeberta":
model = AutoModelForTokenClassification.from_pretrained(
"Pavarissy/mdeberta-v3-ud-thai-pud-upos")
tokenizer = AutoTokenizer.from_pretrained("Pavarissy/mdeberta-v3-ud-thai-pud-upos")
elif engine == "bert-base-th-cased-blackboard":
elif engine == "bert_cased":
model = AutoModelForTokenClassification.from_pretrained("lunarlist/pos_thai")
tokenizer = AutoTokenizer.from_pretrained("lunarlist/pos_thai")
elif engine == "phayathai":
model = AutoModelForTokenClassification.from_pretrained(
"lunarlist/pos_thai_phayathai")
tokenizer = AutoTokenizer.from_pretrained("lunarlist/pos_thai_phayathai")
else:
raise ValueError(
"pos_tag_transformers not support {0} engine.".format(
Expand Down
8 changes: 5 additions & 3 deletions tests/test_tag.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -367,10 +367,12 @@ def test_NNER_class(self):

def test_pos_tag_transformers(self):
self.assertIsNotNone(pos_tag_transformers(
words="แมวทำอะไรตอนห้าโมงเช้า", engine="bert-base-th-cased-blackboard"))
words="แมวทำอะไรตอนห้าโมงเช้า", engine="bert_cased"))
self.assertIsNotNone(pos_tag_transformers(
words="แมวทำอะไรตอนห้าโมงเช้า", engine="mdeberta-v3-ud-thai-pud-upos"))
words="แมวทำอะไรตอนห้าโมงเช้า", engine="mdeberta"))
self.assertIsNotNone(pos_tag_transformers(
words="แมวทำอะไรตอนห้าโมงเช้า", engine="wangchanberta-ud-thai-pud-upos"))
words="แมวทำอะไรตอนห้าโมงเช้า", engine="wangchanberta"))
self.assertIsNotNone(pos_tag_transformers(
words="แมวทำอะไรตอนห้าโมงเช้า", engine="phayathai"))
with self.assertRaises(ValueError):
pos_tag_transformers(words="แมวทำอะไรตอนห้าโมงเช้า", engine="non-existing-engine")