Commit Graph

383 Commits

Author SHA1 Message Date
mrq
9657c1d4ce oops 2023-03-21 20:31:01 +00:00
mrq
0c2a9168f8 DLAS is PIPified (but I'm still cloning it as a submodule to make updating it easier) 2023-03-21 15:46:53 +00:00
mrq
34ef0467b9 VALL-E config edits 2023-03-20 01:22:53 +00:00
mrq
2e33bf071a forgot to not require it to be relative 2023-03-19 22:05:33 +00:00
mrq
5cb86106ce option to set results folder location 2023-03-19 22:03:41 +00:00
mrq
74510e8623 doing what I do best: sourcing other configs and banging until it works (it doesnt work) 2023-03-18 15:16:15 +00:00
mrq
da9b4b5fb5 tweaks 2023-03-18 15:14:22 +00:00
mrq
f44895978d brain worms 2023-03-17 20:08:08 +00:00
mrq
b17260cddf added japanese tokenizer (experimental) 2023-03-17 20:04:40 +00:00
mrq
f34cc382c5 yammed 2023-03-17 18:57:36 +00:00
mrq
96b7f9d2cc yammed 2023-03-17 13:08:34 +00:00
mrq
249c6019af cleanup, metrics are grabbed for vall-e trainer 2023-03-17 05:33:49 +00:00
mrq
1b72d0bba0 forgot to separate phonemes by spaces for [redacted] 2023-03-17 02:08:07 +00:00
mrq
d4c50967a6 cleaned up some prepare dataset code 2023-03-17 01:24:02 +00:00
mrq
0b62ccc112 setup bnb on windows as needed 2023-03-16 20:48:48 +00:00
mrq
c4edfb7d5e unbump rocm5.4.2 because it does not work for me desu 2023-03-16 15:33:23 +00:00
mrq
520fbcd163 bumped torch up (CUDA: 11.8, ROCm, 5.4.2) 2023-03-16 15:09:11 +00:00
mrq
1a8c5de517 unk hunting 2023-03-16 14:59:12 +00:00
mrq
46ff3c476a fixes v2 2023-03-16 14:41:40 +00:00
mrq
0408d44602 fixed reload tts being broken due to being as untouched as I am 2023-03-16 14:24:44 +00:00
mrq
aeb904a800 yammed 2023-03-16 14:23:47 +00:00
mrq
f9154c4db1 fixes 2023-03-16 14:19:56 +00:00
mrq
54f2fc792a ops 2023-03-16 05:14:15 +00:00
mrq
0a7d6f02a7 ops 2023-03-16 04:54:17 +00:00
mrq
4ac43fa3a3 I forgot I undid the thing in DLAS 2023-03-16 04:51:35 +00:00
mrq
da4f92681e oops 2023-03-16 04:35:12 +00:00
mrq
ee8270bdfb preparations for training an IPA-based finetune 2023-03-16 04:25:33 +00:00
mrq
7b80f7a42f fixed not cleaning up states while training (oops) 2023-03-15 02:48:05 +00:00
mrq
b31bf1206e oops 2023-03-15 01:51:04 +00:00
mrq
d752a22331 print a warning if automatically deduced batch size returns 1 2023-03-15 01:20:15 +00:00
mrq
f6d34e1dd3 and maybe I should have actually tested with ./models/tokenizers/ made 2023-03-15 01:09:20 +00:00
mrq
5e4f6808ce I guess I didn't test on a blank-ish slate 2023-03-15 00:54:27 +00:00
mrq
363d0b09b1 added options to pick tokenizer json and diffusion model (so I don't have to add it in later when I get bored and add in diffusion training) 2023-03-15 00:37:38 +00:00
mrq
07b684c4e7 removed redundant training data (they exist within tortoise itself anyways), added utility: view tokenized text 2023-03-14 21:51:27 +00:00
mrq
469dd47a44 fixes #131 2023-03-14 18:58:03 +00:00
mrq
84b7383428 fixes #134 2023-03-14 18:52:56 +00:00
mrq
4b952ea52a fixes #132 2023-03-14 18:46:20 +00:00
mrq
fe03ae5839 fixes 2023-03-14 17:42:42 +00:00
mrq
9d2c7fb942 cleanup 2023-03-14 16:23:29 +00:00
mrq
65fe304267 fixed broken graph displaying 2023-03-14 16:04:56 +00:00
mrq
7b16b3e88a ;) 2023-03-14 15:48:09 +00:00
mrq
c85e32ff53 (: 2023-03-14 14:08:35 +00:00
mrq
54036fd780 :) 2023-03-14 05:02:14 +00:00
mrq
92a05d3c4c added PYTHONUTF8 to start/train bats 2023-03-14 02:29:11 +00:00
mrq
dadb1fca6b multichannel audio now report correct duration (surprised it took this long for me to source multichannel audio) 2023-03-13 21:24:51 +00:00
mrq
32d968a8cd (disabled by default until i validate it working) added additional transcription text normalization (something else I'm experimenting with requires it) 2023-03-13 19:07:23 +00:00
mrq
66ac8ba766 added mel LR weight (as I finally understand when to adjust the text), added text validation on dataset creation 2023-03-13 18:51:53 +00:00
mrq
ee1b048d07 when creating the train/validatio datasets, use segments if the main audio's duration is too long, and slice to make the segments if they don't exist 2023-03-13 04:26:00 +00:00
mrq
0cf9db5e69 oops 2023-03-13 01:33:45 +00:00
mrq
050bcefd73 resample to 22.5K when creating training inputs (to avoid redundant downsampling when loaded for training, even though most of my inputs are already at 22.5K), generalized resampler function to cache and reuse them, do not unload whisper when done transcribing since it gets unloaded anyways for any other non-transcription task 2023-03-13 01:20:55 +00:00