Time stuff and switch to gensim for tokenisation

2022-10-01 14:46:45 +01:00
parent 40cf0c6430
commit 817bfd8835
4 changed files with 100 additions and 41 deletions
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -16,7 +16,8 @@ COPY requirements.txt /code/
 COPY discord-patched.tgz /code/

 RUN python -m venv /venv
-RUN . /venv/bin/activate && pip install -r requirements.txt && python -m spacy download en_core_web_sm
+RUN . /venv/bin/activate && pip install -r requirements.txt
+# && python -m spacy download en_core_web_sm

 RUN tar xf /code/discord-patched.tgz -C /venv/lib/python3.10/site-packages

--- a/docker/requirements.txt
+++ b/docker/requirements.txt
@@ -15,7 +15,8 @@ pycld2
 morfessor
 six
 nltk
-spacy
+#spacy
+gensim
 python-Levenshtein
 orjson
 uvloop