Skip to content

add use_cuda parameter #4

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

Open
mjfox3 wants to merge 4 commits into
base: master
Choose a base branch
from
Open

add use_cuda parameter #4

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9b7c73a
add use_cuda parameter
Jan 13, 2022
0731029
add silent True/False parameter
Jan 14, 2022
4ba590c
add diagnostic prints
Jan 14, 2022
f36df08
add local model capabilities
Feb 3, 2022
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
10 changes: 6 additions & 4 deletions rpunct/punctuate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,14 +10,14 @@


class RestorePuncts:
def __init__(self, wrds_per_pred=250):
def __init__(self, model='felflare/bert-restore-punctuation', wrds_per_pred=250, use_cuda=False, silent=False):
self.wrds_per_pred = wrds_per_pred
self.overlap_wrds = 30
self.valid_labels = ['OU', 'OO', '.O', '!O', ',O', '.U', '!U', ',U', ':O', ';O', ':U', "'O", '-O', '?O', '?U']
self.model = NERModel("bert", "felflare/bert-restore-punctuation", labels=self.valid_labels,
args={"silent": True, "max_seq_length": 512})
self.model = NERModel("bert", f"{model}", labels=self.valid_labels, use_cuda=use_cuda,
args={"silent": silent, "max_seq_length": 512})

def punctuate(self, text: str, lang:str=''):
def punctuate(self, text: str, lang: str = ''):
"""
Performs punctuation restoration on arbitrarily large text.
Detects if input is not English, if non-English was detected terminates predictions.
Expand All @@ -38,8 +38,10 @@ def punctuate(self, text: str, lang:str=''):
splits = self.split_on_toks(text, self.wrds_per_pred, self.overlap_wrds)
# predict slices
# full_preds_lst contains tuple of labels and logits
print(f'predicting {len(splits)} slices')
full_preds_lst = [self.predict(i['text']) for i in splits]
# extract predictions, and discard logits
print(f'combining predictions')
preds_lst = [i[0][0] for i in full_preds_lst]
# join text slices
combined_preds = self.combine_results(text, preds_lst)
Expand Down