Bpemb hot fix (#229)

* hot-fix the problem with BPEmb broken base URL

* add changelog

CHANGELOG.md

@@ -345,4 +345,5 @@
 - Fix app errors.
 - Add data validation for 1) multiple consecutive whitespace and 2) newline.
 - Fixes some errors in tests.
-- Add an argument to the `DatasetContainer` interface to use a pre-processing data cleaning function before validation.
+- Add an argument to the `DatasetContainer` interface to use a pre-processing data cleaning function before validation.
+- Hot-fix the issue with BPEmb base URL download problem see [issue 221](https://github.com/GRAAL-Research/deepparse/issues/221).

deepparse/embeddings_models/bpemb_embeddings_model.py

@@ -4,13 +4,18 @@
 
 import requests
 from bpemb import BPEmb
-
 from numpy.core.multiarray import ndarray
 from urllib3.exceptions import InsecureRequestWarning
 
 from .embeddings_model import EmbeddingsModel
 
 
+class BPEmbBaseURLWrapperBugFix(BPEmb):
+    def __init__(self, **kwargs):
+        self.base_url = "https://bpemb.h-its.org/multi/"
+        super().__init__(**kwargs)
+
+
 class BPEmbEmbeddingsModel(EmbeddingsModel):
     """
     BPEmb embeddings network from `BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages
@@ -31,7 +36,9 @@ def __init__(self, cache_dir: str, verbose: bool = True) -> None:
             # hotfix until https://github.com/bheinzerling/bpemb/issues/63
             # is resolved.
             with no_ssl_verification():
-                model = BPEmb(lang="multi", vs=100000, dim=300, cache_dir=Path(cache_dir))  # defaults parameters
+                # We use the default parameters other than the dim at 300 and a vs of 100,000
+                # We use a BPEmb wrapper since the base URL is broken and the issue is not resolved as of june 23rd.
+                model = BPEmbBaseURLWrapperBugFix(lang="multi", vs=100000, dim=300, cache_dir=Path(cache_dir))
         self.model = model
 
     def __call__(self, word: str) -> ndarray: