every_holiday/VRCT
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

🐛[bugfix] Model : 翻訳処理のマスク処理

Browse Source 
まだ一部バグあり
This commit is contained in:
misyaguziya
2024-05-09 11:51:24 +09:00
parent 4b9255d3dd
commit 23c2fa1119
3 changed files with 44 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
models/translation/translation_translator.py
View File

@@ -52,6 +52,18 @@ class Translator():
self.ctranslate2_translator = None
self.ctranslate2_tokenizer = None
def translateCTranslate2(self, message, source_language, target_language):
try:
self.ctranslate2_tokenizer.src_lang = source_language
source = self.ctranslate2_tokenizer.convert_ids_to_tokens(self.ctranslate2_tokenizer.encode(message))
target_prefix = [self.ctranslate2_tokenizer.lang_code_to_token[target_language]]
results = self.ctranslate2_translator.translate_batch([source], target_prefix=[target_prefix])
target = results[0].hypotheses[0][1:]
result = self.ctranslate2_tokenizer.decode(self.ctranslate2_tokenizer.convert_tokens_to_ids(target))
except Exception:
result = False
return result
@staticmethod
def getLanguageCode(translator_name, target_country, source_language, target_language):
match translator_name:
@@ -115,12 +127,11 @@ class Translator():
to_language=target_language,
)
case "CTranslate2":
self.ctranslate2_tokenizer.src_lang = source_language
source = self.ctranslate2_tokenizer.convert_ids_to_tokens(self.ctranslate2_tokenizer.encode(message))
target_prefix = [self.ctranslate2_tokenizer.lang_code_to_token[target_language]]
results = self.ctranslate2_translator.translate_batch([source], target_prefix=[target_prefix])
target = results[0].hypotheses[0][1:]
result = self.ctranslate2_tokenizer.decode(self.ctranslate2_tokenizer.convert_tokens_to_ids(target))
result = self.translateCTranslate2(
message=message,
source_language=source_language,
target_language=target_language,
)
except Exception:
import traceback
with open('error.log', 'a') as f: