Commit Graph

32 Commits

Author SHA1 Message Date
mrq
277dcec484 apparently I got an error for trying to serialize an errant tensor that made its way into the json, this could be remedied easily with recursively traversing the dict and coercing any objects to primitives, but I'm tired and I just want to start training and nap 2024-05-04 12:33:43 -05:00
mrq
545162195b deprecate sole AR/NAR model by only keeping the AR+NAR (the beauty of no one using this is that I can break compat as much as I want), add tone token for when I classify my dataset with tone/emotion in the future, some other things 2024-04-15 19:54:32 -05:00
mrq
35d78a2bb0 Yet Another Underlying Transformer Implementation (BitNet, will give it a few days to see how it fares) 2024-02-29 20:29:17 -06:00
mrq
0db3203b21 added LLaMA/Mixtral (if experts>1) model arches, utilize XMoE's loss as well, set MoE frequency to 1 to make every layer MoE'd for RetNet, etc. (going to do tests without burning out again to see how things go) 2023-12-22 19:27:36 -06:00
mrq
6c51a629cc resetting step count resets the samples processed and other metrics 2023-10-29 12:11:19 -05:00
mrq
fb467b19ba exposed rolling resp context to the web UI, added passing in language to inferencing command line 2023-10-12 23:21:01 -05:00
mrq
99e980d323 documentation and more better-er attribution 2023-10-10 17:15:16 -05:00
mrq
1fd91b6437 cleanup 2023-10-06 10:13:54 -05:00
mrq
d12877ee09 added option to set probability of selecting the AR during training under a monolithic AR+NAR, added some more to-dos while I have them in mind 2023-10-02 16:52:42 -05:00
mrq
4abd6564d1 fixed training stats not loading from exported weights, a bit of a readme cleanup, updated example training yaml 2023-09-23 19:59:00 -05:00
mrq
a6bfe43590 added mirostat sampling (given a partially trained model, it got far decent output than I expected, need to test on a better trained model) 2023-09-18 18:55:41 -05:00
mrq
23a5fdd645 implemented a naive beam search (I really should be taking a break) 2023-09-12 21:28:07 -05:00
mrq
5ac119a6e7 added light web UI (need to port the telemetry disabling bandaids from aivc) 2023-09-09 16:17:20 -05:00
mrq
10c34c5b98 added a length-based decay factor for repetition penalty 2023-09-08 21:02:00 -05:00
mrq
b922f35b6b added documentation on how these new sampling parameters are very iffy and you really need to know what you are doing to use them because this is audio generation and not text generation 2023-09-08 20:43:36 -05:00
mrq
4613781e23 integrated plot script, added tts-c task token to help the model be able to mix between normal VALL-E and VALL-E continuous 2023-09-02 16:29:53 -05:00
mrq
f7e942ec99 modified plotting script to be more agnostic to X 2023-09-02 13:59:43 -05:00
mrq
6455a2f9d7 I think I fixed a bug? 2023-08-24 23:33:36 -05:00
mrq
f3fbed5ffd updated notices tailored for windows / low VRAM cards 2023-08-24 17:19:10 -05:00
mrq
00ad4af651 updated draconian requirement for espeak-ng to be installed and the env var set to the dll for Windows 2023-08-24 14:57:01 -05:00
mrq
9c5a33bfd2 added repo with my weights so far 2023-08-22 13:09:44 -05:00
mrq
f7f6d3bf6d validated that SpeechX tasks cse and nse works, added a method to test each task by invoking python3 -m vall_e.data --action=tasks --tasks='sr,se,cse,nse' 2023-08-19 09:50:07 -05:00
mrq
0b46c1e312 god I am inexperienced with retaining compat from previous weights, I hope no one actually has weights 2023-08-18 21:29:20 -05:00
mrq
fb4e816823 oops 2023-08-18 21:11:19 -05:00
mrq
ee58db746f actually make the evaluation dataset shuffled for sample_type=speaker 2023-08-17 15:04:45 -05:00
mrq
d7152fc7b9 added pruning of old checkpoints if specified (cfg.trainer.keep_last_checkpoints) 2023-08-16 20:12:12 -05:00
mrq
1e3e1d9315 tweaks 2023-08-15 21:58:16 -05:00
mrq
13571380be made exporter make more sense 2023-08-13 22:56:28 -05:00
mrq
d7deaf6def distributed training works now (hopefully) 2023-08-13 22:07:45 -05:00
mrq
608c1970eb ops 2023-08-03 20:36:19 -05:00
mrq
d88e43800b adjustments 2023-08-02 22:01:49 +00:00
mrq
bf8cedc9dd Rewrite init 2023-08-02 21:53:35 +00:00