DL-Art-School/codes
James Betker e959541494 Add position embeddings back into unified_voice
I think this may be the solution behind the days problems.
2021-12-25 23:10:56 -07:00
..
.idea
data Fix DS 2021-12-25 15:28:59 -07:00
models Add position embeddings back into unified_voice 2021-12-25 23:10:56 -07:00
scripts One way decoder for decoding from mel codes 2021-12-25 12:18:00 -07:00
trainer Support adamw_zero 2021-12-25 21:32:01 -07:00
utils Add use_gpt_tts script 2021-12-16 23:28:54 -07:00
multi_modal_train.py
process_video.py
requirements.txt Remove obsolete lucidrains DALLE stuff, re-create it in a dedicated folder 2021-12-22 13:44:02 -07:00
test.py
train.py UnifiedGptVoice! 2021-12-23 15:20:26 -07:00
use_discriminator_as_filter.py Various mods to support better jpeg image filtering 2021-06-25 13:16:15 -06:00