James Betker 48e3ee9a5b Shuffle conditioning inputs along the positional axis to reduce fitting on prosody and other positional information ... The mels should still retain some short-range positional information the model can use for tone and frequencies, for example.		2021-12-20 19:05:56 -07:00
..
dvae_arch_playground
__init__.py
gpt_asr_hf.py
gpt_asr_hf2.py
gpt_asr.py
gpt_audio_segmentor.py
gpt_tts_hf.py	Shuffle conditioning inputs along the positional axis to reduce fitting on prosody and other positional information	2021-12-20 19:05:56 -07:00
gpt_tts.py
lucidrains_dvae.py
lucidrains_gpt.py
mini_encoder.py
pixelshuffle_1d.py
reversible.py
unet_diffusion_vocoder_with_ref.py