spacy-words-separation2
This commit is contained in:
parent
56a2632980
commit
7030e58f4b
|
@ -6,11 +6,14 @@ WORKDIR /app
|
|||
COPY requirements.txt .
|
||||
|
||||
# Install system dependencies required for building Python packages
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends gcc libffi-dev libssl-dev
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends wget gcc libffi-dev libssl-dev
|
||||
|
||||
# Install Python dependencies including redis with hiredis support
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
|
||||
# Download and install the Russian language model
|
||||
RUN python -m spacy download ru_core_news_md
|
||||
|
||||
COPY . .
|
||||
|
||||
EXPOSE 8080
|
||||
|
|
|
@ -1,7 +1,8 @@
|
|||
import spacy
|
||||
from spacy.lang.ru.examples import
|
||||
|
||||
# Load the Russian language model
|
||||
nlp = spacy.load("ru_core_news_sm")
|
||||
nlp = spacy.load("ru_core_news_md")
|
||||
|
||||
def segment_text(text):
|
||||
"""
|
||||
|
@ -11,7 +12,7 @@ def segment_text(text):
|
|||
doc = nlp(text)
|
||||
|
||||
# Extract words from the processed document
|
||||
segmented_text = ' '.join([token.text for token in doc])
|
||||
segmented_text = ' '.join([token.text for token in doc if not token.is_space])
|
||||
|
||||
return segmented_text
|
||||
|
||||
|
|
|
@ -4,5 +4,3 @@ aiofiles
|
|||
spacy
|
||||
transformers
|
||||
easyocr
|
||||
# protobuf
|
||||
# sentencepiece
|
Loading…
Reference in New Issue
Block a user