Tanay Mehta 182b83749a Add Number Normalisation for SpeechT5 (#25447) ... * add: NumberNormalizer works for integers, floats, common currencies, negative numbers and percentages * fix: renamed number normalizer class and added normalization to SpeechT5Processor * fix: restyled with black and ruff, should pass code quality tests * fix: moved normalization to tokenizer and other small changes to normalizer * add: test for normalization and changed the existing full tokenizer test * fix: tokenization tests now pass, made changes to existing tokenization where normalization is covered; added normalize arg to func signature * fix: changed default normalize setting to False, modified the tests a bit * fix: added support for comma separated numbers, tokenization on the fly with kwargs and normalizer getter setter funcs		2023-08-22 08:12:57 +02:00
..
__init__.py	[WIP] add SpeechT5 model (#18922)	2023-02-03 12:43:46 -05:00
test_feature_extraction_speecht5.py	Fix audio feature extractor deps (#24636)	2023-07-04 16:03:27 +01:00
test_modeling_speecht5.py	add generate method to SpeechT5ForTextToSpeech (#25233)	2023-08-03 14:12:07 +01:00
test_processor_speecht5.py	TTS fine-tuning for SpeechT5 (#21824)	2023-04-18 10:12:30 +01:00
test_tokenization_speecht5.py	Add Number Normalisation for SpeechT5 (#25447)	2023-08-22 08:12:57 +02:00