explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-13 13:17:06 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add option to download speech-parsing data set.

Browse Source
This commit is contained in:
Matthew Honnibal 2015-02-11 14:20:29 -05:00
parent 0b7e769211
commit 594e50bd45
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/en/download.py
View File

@ -15,6 +15,8 @@ ALL_DATA_DIR_URL = '%s/en_data_all-%s.tgz' % (AWS_STORE, VERSION)
SM_DATA_DIR_URL = '%s/en_data_sm-%s.tgz' % (AWS_STORE, VERSION) SM_DATA_DIR_URL = '%s/en_data_sm-%s.tgz' % (AWS_STORE, VERSION)
SPEECH_DATA_DIR_URL = '%s/en_data_speech-%s.tgz' % (AWS_STORE, VERSION)
DEST_DIR = path.join(path.dirname(__file__), 'data') DEST_DIR = path.join(path.dirname(__file__), 'data')
@ -44,6 +46,8 @@ def install_dep_vectors(url, dest_dir):
def main(data_size='all'): def main(data_size='all'):
if data_size == 'all': if data_size == 'all':
data_url = ALL_DATA_DIR_URL data_url = ALL_DATA_DIR_URL
elif data_size == 'speech':
data_url = SPEECH_DATA_DIR_URL
elif data_size == 'small': elif data_size == 'small':
data_url = SM_DATA_DIR_URL data_url = SM_DATA_DIR_URL
if path.exists(DEST_DIR): if path.exists(DEST_DIR):