forked from mrq/DL-Art-School
parametric efficiency improvements and lets try feeding the timestep into the conditioning encoder |
||
---|---|---|
.. | ||
__init__.py | ||
diffwave.py | ||
flat_diffusion.py | ||
gpt_music.py | ||
gpt_music2.py | ||
m2v_code_to_mel.py | ||
mel2vec_codes_gpt.py | ||
music_quantizer.py | ||
music_quantizer2.py | ||
tfdpc_v1.py | ||
tfdpc_v2.py | ||
tfdpc_v3.py | ||
tfdpc_v4.py | ||
transformer_diffusion12.py | ||
unet_diffusion_music_codes.py | ||
unet_diffusion_waveform_gen_simple.py | ||
unet_diffusion_waveform_gen.py | ||
unet_diffusion_waveform_gen3.py |