vall-e/vall_e
2025-02-10 14:43:15 -06:00
..
emb invalidate a path if loading via metadata and entry is not in hdf5 (to avoid reparsing my metadata since I'm using a partial copy of my dataset at the moment) 2025-02-10 14:43:15 -06:00
engines more work (the wall is non-causal decoding......) 2024-12-22 20:11:31 -06:00
models ugh 2025-02-09 13:02:51 -06:00
utils
__init__.py
__main__.py added option to playback audio directly, removed no-phonemize option since I swear it worked in testing but it doesn't actually work 2025-01-12 21:52:49 -06:00
config.py updated vall_e.emb.process to allow for batched processing, some typo fixes (it's painfully slow on my 7900XTX...) 2025-02-05 21:13:20 -06:00
data.py invalidate a path if loading via metadata and entry is not in hdf5 (to avoid reparsing my metadata since I'm using a partial copy of my dataset at the moment) 2025-02-10 14:43:15 -06:00
demo.py
export.py 2024-12-26 21:42:17 -06:00
inference.py added option to playback audio directly, removed no-phonemize option since I swear it worked in testing but it doesn't actually work 2025-01-12 21:52:49 -06:00
metrics.py
plot.py
samplers.py
train.py oops 2025-01-05 23:53:17 -06:00
webui.py added option to playback audio directly, removed no-phonemize option since I swear it worked in testing but it doesn't actually work 2025-01-12 21:52:49 -06:00