mrq 8515038968 imagine my disappointment when the epoch finished just for it to throw an exception		2024-12-16 18:28:01 -06:00
..
emb	KO/ZH model soon	2024-12-15 17:01:14 -06:00
engines	remove nan checks because it causes problems in distributed training because I'm not syncing between GPUs (and nan losses gets ignored anyways with loss scaling)	2024-12-15 09:42:54 -06:00
models	imagine my disappointment when the epoch finished just for it to throw an exception	2024-12-16 18:28:01 -06:00
utils	imagine my disappointment when the epoch finished just for it to throw an exception	2024-12-16 18:28:01 -06:00
__init__.py	Rewrite init	2023-08-02 21:53:35 +00:00
__main__.py	doc update, added automatically deducing language from a given text, also checks if the input is already phonemized text to allow direct control without being cringe (procrastinating adding WER/SIM-O)	2024-12-07 22:34:25 -06:00
config.py	APOLLO tweaks to make it work with deepspeed	2024-12-13 23:03:52 -06:00
data.py	APOLLO cringe (doesn't want to work with deepspeed)	2024-12-12 00:31:58 -06:00
demo.py	more fixes for local engine backend	2024-12-12 14:38:42 -06:00
export.py	cringe code to convert to LlamaForCausalLM-happy weights + tokenizer dict (still need to write logic to actually use these weights for proper inferencing)	2024-12-03 10:18:58 -06:00
inference.py	sort batches to try and reduce number of padded tokens in batched inference (also commented out F5 samples getting added to the demo page because I would have to regenerate them)	2024-12-11 22:45:38 -06:00
metrics.py	uplifting transformer's WavLM stuff to do speaker verification instead	2024-12-11 19:30:05 -06:00
plot.py	very, very naive layerskip speculative sampling (it just checks if the current layer's state is good enough)	2024-11-02 11:49:05 -05:00
samplers.py	sort batches to try and reduce number of padded tokens in batched inference (also commented out F5 samples getting added to the demo page because I would have to regenerate them)	2024-12-11 22:45:38 -06:00
train.py	remove nan checks because it causes problems in distributed training because I'm not syncing between GPUs (and nan losses gets ignored anyways with loss scaling)	2024-12-15 09:42:54 -06:00
webui.py	logic fixes, I feel like output is better? (also NAR can have a temperature, I imagine it couldn't because it was having a causal masked passed to it for the longest time before I caught it a month ago)	2024-12-08 14:52:47 -06:00