Jan Zípek 98080e282c fix(xtts): use correct language code for Czech num2words call (#237) ... * Fix num2words call using non-standard lang code * build: update minimum num2words version --------- Co-authored-by: Enno Hermann <enno.hermann@idiap.ch>		2024-12-28 13:25:46 +01:00
..
trainer	refactor(xtts): remove duplicate xtts audio config	2024-12-05 15:46:28 +01:00
__init__.py	chore(stream_generator): address lint issues	2024-06-17 09:52:35 +02:00
dvae.py	refactor: move exists() and default() into generic_utils	2024-11-24 19:57:14 +01:00
gpt.py	refactor(xtts): use tortoise conditioning encoder	2024-11-24 19:57:14 +01:00
gpt_inference.py	fix(gpt): set attention mask and address other warnings	2024-10-25 18:49:04 +02:00
hifigan_decoder.py	refactor(xtts): remove duplicate hifigan generator	2024-11-21 11:53:35 +01:00
perceiver_encoder.py	refactor: move exists() and default() into generic_utils	2024-11-24 19:57:14 +01:00
stream_generator.py	fix(xtts): support transformers>=4.43.0 in streaming inference	2024-10-20 15:20:26 +02:00
tokenizer.py	fix(xtts): use correct language code for Czech num2words call (#237)	2024-12-28 13:25:46 +01:00
xtts_manager.py	fix: only enable load with weights_only in pytorch>=2.4	2024-11-04 18:39:51 +01:00
zh_num2words.py	fix: use logging instead of print statements	2024-04-03 15:19:45 +02:00