Bump version to 1.0.4

UKPLab · Apr 1, 2021 · 836f822 · 836f822
1 parent a17ec1e
commit 836f822
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 5 deletions.
diff --git a/examples/training/ms_marco/multilingual/translate_queries.py b/examples/training/ms_marco/multilingual/translate_queries.py
@@ -3,12 +3,16 @@
 
 For machine translation, we use EasyNMT: https://github.com/UKPLab/EasyNMT
 You can install it via: pip install easynmt
+
+Usage:
+python translate_queries [target_language]
 """
 import os
 from sentence_transformers import LoggingHandler, util
 import logging
 import tarfile
 from easynmt import EasyNMT
+import sys
 
 #### Just some code to print debug information to stdout
 logging.basicConfig(format='%(asctime)s - %(message)s',
@@ -17,8 +21,10 @@
                     handlers=[LoggingHandler()])
 #### /print debug information to stdout
 
-target_lang = 'de'
+target_lang = sys.argv[1]
 output_folder = 'multilingual-data'
+data_folder = '../msmarco-data'
+
 output_filename = os.path.join(output_folder, 'train_queries.en-{}.tsv'.format(target_lang))
 os.makedirs(output_folder, exist_ok=True)
 
@@ -32,7 +38,6 @@
             translated_qids.add(splits[0])
 
 ### Now we read the MS Marco dataset
-data_folder = '../msmarco-data'
 os.makedirs(data_folder, exist_ok=True)
 
 # Read qrels file for relevant positives per query
@@ -78,5 +83,5 @@
 
 with open(output_filename, 'a' if os.path.exists(output_filename) else 'w', encoding='utf8') as fOut:
     for qid, query, translated_query in zip(qids, queries, translation_model.translate_stream(queries, source_lang='en', target_lang=target_lang, beam_size=2, perform_sentence_splitting=False, chunk_size=256, batch_size=64)):
-        fOut.write("{}\t{}\t{}\n".format(qid, query.replace("\t", " "), translated_query.replace("\t", " ")))
+        fOut.write("{}\t{}\t{}\n".format(qid, translated_query.replace("\t", " ")))
         fOut.flush()
diff --git a/sentence_transformers/__init__.py b/sentence_transformers/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "1.0.3"
+__version__ = "1.0.4"
 __DOWNLOAD_SERVER__ = 'http://sbert.net/models/'
 from .datasets import SentencesDataset, ParallelSentencesDataset
 from .LoggingHandler import LoggingHandler

diff --git a/setup.py b/setup.py
@@ -7,7 +7,7 @@
 
 setup(
     name="sentence-transformers",
-    version="1.0.3",
+    version="1.0.4",
     author="Nils Reimers",
     author_email="[email protected]",
     description="Sentence Embeddings using BERT / RoBERTa / XLM-R",