James Betker 009a1e8404 Add a new diffusion_vocoder that should be trainable faster ... This new one has a "cheating" top layer, that does not feed down into the unet encoder, but does consume the outputs of the unet. This cheater only operates on half of the input, while the rest of the unet operates on the full input. This limits the dimensionality of this last layer, on the assumption that these last layers consume by far the most computation and memory, but do not require the full input context. Losses are only computed on half of the aggregate input.		2022-01-11 17:26:07 -07:00
..
__init__.py	Add gpt_tts	2021-07-27 20:33:30 -06:00
gpt_asr_hf.py	Fix gpt_tts_hf inference	2021-12-20 17:45:26 -07:00
gpt_asr_hf2.py	misc	2022-01-06 22:16:17 -07:00
gpt_tts_hf.py	Make tokenization configs more configurable	2021-12-25 12:17:50 -07:00
lucidrains_dvae.py	Remove dvae_arch_playground	2022-01-05 17:06:45 -07:00
mini_encoder.py	misc	2022-01-01 14:05:33 -07:00
pixelshuffle_1d.py	Improvements to GptTts	2021-07-31 15:57:57 -06:00
text_voice_clip.py	Fixes	2022-01-10 14:32:04 -07:00
transformer_builders.py	unified_voice2: decouple positional embeddings and token embeddings from underlying gpt model	2022-01-10 08:14:41 -07:00
unet_diffusion_vocoder_with_ref_trunc_top.py	Add a new diffusion_vocoder that should be trainable faster	2022-01-11 17:26:07 -07:00
unet_diffusion_vocoder_with_ref.py	misc	2021-12-11 08:17:26 -07:00
unified_voice_bilevel.py	dataset improvements and fix to unified_voice_Bilevel	2022-01-01 00:16:30 -07:00
unified_voice.py	Revert unified_voice back to beginning	2022-01-09 22:34:30 -07:00
unified_voice2.py	fix unified_voice	2022-01-10 16:17:31 -07:00
voice_voice_clip.py	Fix gapping bug in voice2voice clip	2021-12-29 14:44:46 -07:00