forked from mrq/DL-Art-School
a9629f7022
This results in a significant compression of the text domain, I'm curious what the effect on speech quality will be. |
||
---|---|---|
.. | ||
dvae_arch_playground | ||
__init__.py | ||
gpt_asr_hf.py | ||
gpt_asr_hf2.py | ||
gpt_tts_hf.py | ||
lucidrains_dvae.py | ||
mini_encoder.py | ||
pixelshuffle_1d.py | ||
unet_diffusion_vocoder_with_ref.py | ||
voice_clip.py |