heimoshuiyu/faster-whisper
1
0
Fork 0
Code Issues Pull Requests 1 Packages Projects Releases Wiki Activity

Improve error message for invalid task and language parameters (#466)

Browse Source
This commit is contained in:
Guillaume Klein
2023-09-12 10:02:23 +02:00
committed by GitHub
parent 0285d46f6f
commit 727ab81f31
1 changed files with 121 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

128
faster_whisper/tokenizer.py
View File

@@ -19,15 +19,21 @@ class Tokenizer:
self.tokenizer = tokenizer
if multilingual:
if task not in _TASKS:
raise ValueError(
"'%s' is not a valid task (accepted tasks: %s)"
% (task, ", ".join(_TASKS))
)
if language not in _LANGUAGE_CODES:
raise ValueError(
"'%s' is not a valid language code (accepted language codes: %s)"
% (language, ", ".join(_LANGUAGE_CODES))
)
self.task = self.tokenizer.token_to_id("<|%s|>" % task)
if self.task is None:
raise ValueError("%s is not a valid task" % task)
self.language_code = language
self.language = self.tokenizer.token_to_id("<|%s|>" % language)
if self.language is None:
raise ValueError("%s is not a valid language code" % language)
self.language_code = language
else:
self.task = None
self.language = None
@@ -161,3 +167,111 @@ class Tokenizer:
word_tokens[-1].extend(subword_tokens)
return words, word_tokens
_TASKS = (
"transcribe",
"translate",
)
_LANGUAGE_CODES = (
"af",
"am",
"ar",
"as",
"az",
"ba",
"be",
"bg",
"bn",
"bo",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"fi",
"fo",
"fr",
"gl",
"gu",
"ha",
"haw",
"he",
"hi",
"hr",
"ht",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jw",
"ka",
"kk",
"km",
"kn",
"ko",
"la",
"lb",
"ln",
"lo",
"lt",
"lv",
"mg",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"ne",
"nl",
"nn",
"no",
"oc",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"sn",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"tk",
"tl",
"tr",
"tt",
"uk",
"ur",
"uz",
"vi",
"yi",
"yo",
"zh",
)