trankit
trankit copied to clipboard
Hebrew link is broken
Hi, thanks for the great resource!
Link to Hebrew model seems to be broken
BadZipFile Traceback (most recent call last)
Input In [59], in <cell line: 3>()
1 from trankit import Pipeline
----> 3 p = Pipeline(lang='hebrew', gpu=False, cache_dir='./cache')
File ~/opt/anaconda3/envs/ayalon/lib/python3.9/site-packages/trankit/pipeline.py:70, in Pipeline.__init__(self, lang, cache_dir, gpu, embedding)
66 assert lang in lang2treebank, '{} has not been supported. Currently supported languages: {}'.format(lang,
67 list(
68 lang2treebank.keys()))
69 # download saved model for initial language
---> 70 download(
71 cache_dir=self._config._cache_dir,
72 language=lang,
73 saved_model_version=saved_model_version, # manually set this to avoid duplicated storage
74 embedding_name=master_config.embedding_name
75 )
77 # load ALL vocabs
78 self._load_vocabs()
File ~/opt/anaconda3/envs/ayalon/lib/python3.9/site-packages/trankit/utils/base_utils.py:114, in download(cache_dir, language, saved_model_version, embedding_name)
112 file.write(data)
113 progress_bar.close()
--> 114 unzip(lang_dir, '{}.zip'.format(language))
115 if total_size_in_bytes != 0 and progress_bar.n != total_size_in_bytes:
116 print("Failed to download saved models for {}!".format(language))
File ~/opt/anaconda3/envs/ayalon/lib/python3.9/site-packages/trankit/utils/base_utils.py:89, in unzip(dir, filename)
88 def unzip(dir, filename):
---> 89 with zipfile.ZipFile(os.path.join(dir, filename)) as f:
90 f.extractall(dir)
91 os.remove(os.path.join(dir, filename))
File ~/opt/anaconda3/envs/ayalon/lib/python3.9/zipfile.py:1266, in ZipFile.__init__(self, file, mode, compression, allowZip64, compresslevel, strict_timestamps)
1264 try:
1265 if mode == 'r':
-> 1266 self._RealGetContents()
1267 elif mode in ('w', 'x'):
1268 # set the modified flag so central directory gets written
1269 # even if no files are added to the archive
1270 self._didModify = True
File ~/opt/anaconda3/envs/ayalon/lib/python3.9/zipfile.py:1333, in ZipFile._RealGetContents(self)
1331 raise BadZipFile("File is not a zip file")
1332 if not endrec:
-> 1333 raise BadZipFile("File is not a zip file")
1334 if self.debug > 1:
1335 print(endrec)
BadZipFile: File is not a zip file```