James Betker 032983e2ed fix bug and allow position encodings to be trained separately from the rest of the model		2022-04-08 16:26:01 -06:00
..
tacotron2
__init__.py
autoregressive_codegen.py	Align autoregressive text using start and stop tokens	2022-04-08 09:41:59 -06:00
autoregressive_codegen2.py	cg2	2022-04-06 21:24:36 -06:00
ctc_code_generator2.py
diffusion_encoder.py	drop full layers in layerdrop, not half layers	2022-03-23 17:15:08 -06:00
lucidrains_dvae.py
mini_encoder.py
transformer_builders.py	unified_voice with rotary embeddings	2022-04-07 20:11:14 -06:00
unet_diffusion_tts_flat.py	drop full layers in layerdrop, not half layers	2022-03-23 17:15:08 -06:00
unet_diffusion_tts_flat0.py	undo latent converter change	2022-04-01 20:46:27 -06:00
unet_diffusion_tts7.py	support x-transformers in text_voice_clip and support relative positional embeddings	2022-03-26 22:48:10 -06:00
unet_diffusion_tts9.py
unet_diffusion_vocoder_with_ref.py
unet_diffusion_vocoder.py
unified_voice2.py	fix bug and allow position encodings to be trained separately from the rest of the model	2022-04-08 16:26:01 -06:00
voice_voice_clip.py
w2v_matcher.py