Commit Graph

1285 Commits

Author SHA1 Message Date
James Betker
2afea126d7 mod trainer to be very explicit about the fact that loading models and state together dont work, but allow it 2021-10-28 22:32:42 -06:00
James Betker
bb0a0c8264 classify_into_folders script 2021-10-27 14:56:16 -06:00
James Betker
d91dcbd404 Make classifier inference script more open 2021-10-27 13:18:54 -06:00
James Betker
58494b0888 Add support for distilling gpt_asr 2021-10-27 13:10:07 -06:00
James Betker
5d714bc566 Add deepspeech model and support for decoding with it 2021-10-27 13:09:46 -06:00
James Betker
15437b2fc3 WER script 2021-10-26 13:30:29 -06:00
James Betker
3a9d1c53ea Rework conditioning inputs provided 2021-10-26 10:46:33 -06:00
James Betker
21b6daa0ed Introduce clip resampling 2021-10-26 10:42:23 -06:00
James Betker
43e389aac6 Add time_embed_dim_multiplier 2021-10-26 08:55:55 -06:00
James Betker
ba6e46c02a Further simplify diffusion_vocoder and make noise_surfer work 2021-10-26 08:54:30 -06:00
James Betker
c3421b7f6d Dataset work for audio quality processor 2021-10-24 09:09:34 -06:00
James Betker
0ee1c67ce5 Rework how conditioning inputs are applied to DiffusionVocoder 2021-10-24 09:08:58 -06:00
James Betker
b1248e7114 Get rid of filter_urbansounds 2021-10-21 16:46:04 -06:00
James Betker
06ea6191a9 Initial implementation of audio_with_noise dataset 2021-10-21 16:45:19 -06:00
James Betker
9a3e89ec53 Force LR fix 2021-10-21 12:01:01 -06:00
James Betker
40cb25292a Fix force_lr logic 2021-10-21 11:51:30 -06:00
James Betker
0dee15f875 base DVAE & vector_quantizer 2021-10-20 21:19:38 -06:00
James Betker
f2a31702b5 Clean stuff up, move more things into arch_util 2021-10-20 21:19:25 -06:00
James Betker
a6f0f854b9 Fix codes when inferring from dvae 2021-10-17 22:51:17 -06:00
James Betker
d016a2fbad Go back to vanilla flavor of diffusion 2021-10-17 17:32:46 -06:00
James Betker
23da073037 Norm decoder outputs now 2021-10-16 09:07:10 -06:00
James Betker
0edc98f6c4 Throw out the idea of conditioning on discrete codes. Oh well :( 2021-10-16 09:02:01 -06:00
James Betker
62c8c5d93e Zero out spectrogram code inputs initially. 2021-10-15 12:10:11 -06:00
James Betker
1d0b44ebc2 More tweaks to diffusion-vocoder 2021-10-15 11:51:17 -06:00
James Betker
3b19581f9a Allow num_resblocks to specified per-level 2021-10-14 11:26:04 -06:00
James Betker
83798887a8 Mods to support unet diffusion vocoder with conditioning 2021-10-13 21:23:18 -06:00
James Betker
c861054218 Restore spleeter_splitter
The mods don't help - in TF mode, everything is done on the GPU anyways. Something else
is going to have to be done to fix this.
2021-10-09 23:55:42 -06:00
James Betker
32ba496632 More fixes 2021-10-09 23:27:14 -06:00
James Betker
932ea29a83 Add multiprocessing to the spleeter splitter script to try and improve performance further 2021-10-09 23:15:36 -06:00
James Betker
b94e587f46 Improvements to spleeter_filter_noisy_clips 2021-10-07 21:28:00 -06:00
James Betker
33120cb35c Add norming to discretization_loss 2021-10-06 17:10:50 -06:00
James Betker
bb891a3a53 Add partitioning and improved resuming to the spleeter filtering 2021-10-06 17:10:12 -06:00
James Betker
f2977d360c Allow attention_dim in channel attention to be specified, add converter 2021-10-05 17:29:38 -06:00
James Betker
9c0d7288ea Discretization loss attempt 2021-10-04 20:59:21 -06:00
James Betker
66f99a159c Rev2 2021-10-03 15:20:50 -06:00
James Betker
09f373e3b1 Add dvae with channel attention 2021-10-03 10:52:01 -06:00
James Betker
0396a9d2ca Increase baseline codes recording across all dvae models 2021-09-30 08:09:07 -06:00
James Betker
f84ccbdfb2 Fix quantizer with balancing_heuristic 2021-09-29 14:46:05 -06:00
James Betker
4914c526dc More cleanup 2021-09-29 14:24:49 -06:00
James Betker
6e550edfe3 Attentive dvae 2021-09-29 14:17:29 -06:00
James Betker
fc8ae4679a Work on spleeter filtering script 2021-09-29 09:24:56 -06:00
James Betker
55b58fb67f Clean up codebase
Remove stuff that I'm likely not going to use again (or generally failed experiments)
2021-09-29 09:21:44 -06:00
James Betker
4d1a42e944 Add switchnorm to gumbel_quantizer 2021-09-24 18:49:25 -06:00
James Betker
ac57cdc794 Add scheduling to quantizer, enable cudnn_benchmarking to be disabled 2021-09-24 17:01:36 -06:00
James Betker
3e64e847c2 Gumbel quantizer 2021-09-23 23:32:03 -06:00
James Betker
c5297ccec6 Add dvae balancing heuristic 2021-09-23 21:19:36 -06:00
James Betker
e24c619387 Fix 2021-09-23 16:07:58 -06:00
James Betker
6833048bf7 Alterations to diffusion_dvae so it can be used directly on spectrograms 2021-09-23 15:56:25 -06:00
James Betker
97ea329a59 Make spleeter filter simpler (and hopefully much faster) 2021-09-17 15:29:42 -06:00
James Betker
359e9e27a7 unsupervised_audio_dataset: try to recover from failures of audio2numpy 2021-09-17 15:25:57 -06:00
James Betker
5c8d266d4f chk 2021-09-17 09:15:36 -06:00
James Betker
a6544f1684 More checkpointing fixes 2021-09-16 23:12:43 -06:00
James Betker
94899d88f3 Fix overuse of checkpointing 2021-09-16 23:00:28 -06:00
James Betker
f78ce9d924 Get diffusion_dvae ready for prime time! 2021-09-16 22:43:10 -06:00
James Betker
1197ae1928 Misc 2021-09-16 10:53:56 -06:00
James Betker
6f48674647 Support diffusion models with extra return values & inference in diffusion_dvae 2021-09-16 10:53:46 -06:00
James Betker
8d9857f33d More fixes 2021-09-14 20:45:05 -06:00
James Betker
9a9c90660f Fixes 2021-09-14 18:29:17 -06:00
James Betker
4334a67924 Spleeter mods 2021-09-14 17:43:40 -06:00
James Betker
0382660159 Get diffusion_dvae functional 2021-09-14 17:43:31 -06:00
James Betker
e513052fca Add unsupervised_audio_dataset 2021-09-14 17:43:16 -06:00
James Betker
bc603c3231 Script adjustments and fixes 2021-09-12 21:26:45 -06:00
James Betker
76e2c497f7 Improvements to splitter 2021-09-09 23:34:56 -06:00
James Betker
742f9b4010 Batch spleeter cleaner using GPU 2021-09-09 23:14:32 -06:00
James Betker
73b930c0f6 Add diffusion_dvae
Increase split_on_silence interval
2021-09-09 16:22:05 -06:00
James Betker
b8f2e0f452 mydvae 2021-09-06 17:45:30 -06:00
James Betker
92e7e57f81 Update diffusion_noise_surfer to support audio 2021-09-01 08:34:47 -06:00
James Betker
3e073cff85 Set kernel_size in diffusion_vocoder 2021-09-01 08:33:46 -06:00
James Betker
30cd33fe44 another fix 2021-08-31 14:46:46 -06:00
James Betker
8810d3de97 fix wavfile_dataset 2021-08-31 14:45:29 -06:00
James Betker
dabd87246d Add unet_diffusion_vocoder 2021-08-31 14:38:33 -06:00
James Betker
274d352e6f dug 2021-08-30 21:45:58 -06:00
James Betker
f1a0c21fb2 asr_eval 2021-08-30 21:41:34 -06:00
James Betker
ed6eae407f More scripts for splitting and formatting audio 2021-08-30 21:20:52 -06:00
James Betker
909754cc27 Add find_faulty_files.py 2021-08-25 18:00:43 -06:00
James Betker
08b33c8e3a Support silu activation 2021-08-25 09:03:14 -06:00
James Betker
67bf7f5219 dvae mods
Trying to squeeze as much performance out of this net as possible
2021-08-25 08:55:13 -06:00
James Betker
d05cc1f46c Misc 2021-08-24 17:12:04 -06:00
James Betker
9dfe936c16 Fix ddp for sampler 2021-08-19 16:45:34 -06:00
James Betker
b521d94b01 Make gpt-asr more configurable 2021-08-19 16:33:41 -06:00
James Betker
570ed327ed Stop dataset - attempt #2 2021-08-18 18:29:38 -06:00
James Betker
17453ccbe8 Revert mods to lrdvae
They didn't really change anything
2021-08-17 09:09:29 -06:00
James Betker
8332923f5c Two more tools to test the audio segmentor 2021-08-17 09:09:11 -06:00
James Betker
7c086d0c2c libritts - only write on successful check 2021-08-16 22:52:55 -06:00
James Betker
93e903af15 Rework wavfile dataset to be usable for things other than augments 2021-08-16 22:52:35 -06:00
James Betker
d7f30232c3 Oh yeah 2021-08-16 22:52:15 -06:00
James Betker
4c01d82265 Fix for voxpopuli 2021-08-16 22:52:05 -06:00
James Betker
1fede41b7b Audio segmentor 2021-08-16 22:51:53 -06:00
James Betker
2d3372054d Add support for voxpopuli to nv_tacotron_dataset 2021-08-16 17:13:40 -06:00
James Betker
729c1fd5a9 Fix up max lengths to save memory 2021-08-15 21:29:28 -06:00
James Betker
9e47e64d5a Add gpt_segmentor model
The idea is to specifically train a model that extracts phrases from
audio clips.
2021-08-15 21:23:07 -06:00
James Betker
a826d5f658 Mods to dvae
- Add resblock to each layer
- Increase filter size for each layer
- Use SiLU
2021-08-15 20:54:10 -06:00
James Betker
b8bec22f1a Fix gpt_asr inference bug 2021-08-15 20:53:42 -06:00
James Betker
3580c52eac Fix up wavfile_dataset to be able to provide a full clip 2021-08-15 20:53:26 -06:00
James Betker
a523c4f932 Auto-normalize wav files by data type 2021-08-15 09:09:51 -06:00
James Betker
98057b6516 Make lrdvae use quantized mode in eval() 2021-08-14 23:43:01 -06:00
James Betker
c28f657ab8 Allow usage of pre-rendered mels saved to npy files 2021-08-14 23:38:15 -06:00
James Betker
ad3391bd96 Fix nan issue when interpolating audio 2021-08-14 20:42:01 -06:00
James Betker
769f0acc53 Moar fix 2021-08-14 17:23:15 -06:00
James Betker
3d2e724083 Fix audio ranging problem 2021-08-14 17:18:55 -06:00
James Betker
d6a73acaed Allow processing of multiple audio sources at once from nv_tacotron_dataset 2021-08-14 16:04:05 -06:00
James Betker
007976082b GPT_asr for inference 2021-08-14 14:37:17 -06:00
James Betker
e1bdd3f7c7 Fix gpt_asr bug. Initial implementation of beam search 2021-08-13 22:47:00 -06:00
James Betker
72622b4d61 Allow saving mel strips as files from the dataset implementation 2021-08-13 22:46:41 -06:00
James Betker
cfd284f425 Fix up some stuff that allows the MEL to be computed on-GPU 2021-08-13 18:35:55 -06:00
James Betker
cdee31c60b GPT_ASR 2021-08-13 15:02:18 -06:00
James Betker
81e91c99de Misc 2021-08-13 13:58:59 -06:00
James Betker
fff1a59e08 max/min mel invalid fix 2021-08-13 09:36:31 -06:00
James Betker
4b2946e581 More fix 2021-08-12 15:51:23 -06:00
James Betker
4c76257c71 Dont require collation for nv_tacotron 2021-08-12 15:44:55 -06:00
James Betker
5b07d3b623 Found error that I was trying to fix with reload=True 2021-08-12 15:22:34 -06:00
James Betker
430b650a34 ...... 2021-08-12 10:31:10 -06:00
James Betker
b35d6ae028 Print some metrics from tacotron dataset when it croaks 2021-08-12 09:21:12 -06:00
James Betker
0c4d6b1916 Just offer generic re-load for nv-tacotron 2021-08-12 09:09:12 -06:00
James Betker
154f5aa73c Fix annoying warning and add to requirements 2021-08-11 17:32:06 -06:00
James Betker
f5a9b88ef6 tacotron cleaners: remove quotation marks
these don't really have relevance for tts or asr
2021-08-11 16:18:44 -06:00
James Betker
20586a8edc Fix LRDVAE bug with quantizer integration 2021-08-11 16:17:22 -06:00
James Betker
f04a7bdf63 Bug fixes for tacotron dataset on mozilla cv
- Support a max mel length (mozilla cv has some tracks that are basically unbounded..)
- Don't fail on low sample rates (mozilla cv has some of those)
2021-08-11 16:17:03 -06:00
James Betker
2d3f0cc33c nv_tacotron_dataset - Allow training on mozilla cv 2021-08-11 13:34:31 -06:00
James Betker
d0c74278bf Enable multiple wavfile paths to be specified, fix eps bug in mp3 splitter 2021-08-11 08:46:02 -06:00
James Betker
e19c00398e More improvements to random_mp3_splitter 2021-08-09 21:31:12 -06:00
James Betker
04d14b3acc No batch factors for eval 2021-08-09 16:02:01 -06:00
James Betker
82fc69abfa Add "pure" evaluator
Which simply computes the training loss against an eval dataset
2021-08-09 14:58:35 -06:00
James Betker
080bea2f19 No, really 2021-08-09 12:02:31 -06:00
James Betker
e1ce4671e4 Apply dropout to gpt_tts, get rid of min_gpt implementation 2021-08-09 12:01:10 -06:00
James Betker
74342b860b Revert "Undo forced text padding"
This reverts commit 83ab5e6a00.
2021-08-09 11:56:34 -06:00
James Betker
1068f53b78 Add a sampling beam search 2021-08-09 11:56:06 -06:00
James Betker
d4e33bf15f Fixes to the mp3 splitter 2021-08-09 11:55:46 -06:00
James Betker
4100469902 Add a tool to split mp3 files into arbitrary chunks of wav files 2021-08-08 23:23:13 -06:00
James Betker
01cfae28d8 Beam search implementation in one pass? Dayyyum 2021-08-08 23:22:42 -06:00
James Betker
83ab5e6a00 Undo forced text padding 2021-08-08 11:42:20 -06:00
James Betker
690d7e86d3 Fix nv_tacotron_dataset bug which incorrectly mapped filenames
dammit..
2021-08-08 11:38:52 -06:00
James Betker
a2afb25e42 Fix inference, always flow full text tokens through transformer 2021-08-07 20:11:10 -06:00
James Betker
4c678172d6 ugh 2021-08-06 22:10:18 -06:00
James Betker
e723137273 Make gpttts more configurable 2021-08-06 22:08:51 -06:00
James Betker
a7496b661c combined dvae ftw 2021-08-06 22:01:06 -06:00
James Betker
0237e96b34 Fix dvae bug 2021-08-06 14:17:01 -06:00
James Betker
0799d95af5 Use quantizer from rosinality/vqvae with openai dvae 2021-08-06 14:06:26 -06:00
James Betker
d3ace153af Add logic for performing inference using gpt_tts with dual-encoder modes 2021-08-06 12:04:12 -06:00
James Betker
b43683b772 Add lucidrains_dvae 2021-08-06 12:03:46 -06:00
James Betker
62c7570512 Constrain wav_aug a bit more 2021-08-06 08:19:38 -06:00
James Betker
f126040da2 Undo noise first 2021-08-05 23:24:38 -06:00
James Betker
908ef5495f Add noise first to audio_aug 2021-08-05 23:22:44 -06:00
James Betker
d6007c6de1 dataset fixes 2021-08-05 23:12:59 -06:00
James Betker
3ca51e80b2 Only fix weird path bug in windows 2021-08-05 22:21:25 -06:00
James Betker
70dcd1107f Fix byol_model_wrapper to function with audio inputs 2021-08-05 22:20:22 -06:00
James Betker
f86df53ce0 Export extract_byol_model as a function 2021-08-05 22:15:26 -06:00
James Betker
89d15c9e74 Move gpt-tts back to lucidrains implementation
Much better performance.
2021-08-05 22:15:13 -06:00
James Betker
d120e1aa99 Add audio augmentation to wavfile_dataset, utility to test audio similary 2021-08-05 22:14:49 -06:00
James Betker
c0f61a2e15 Rework how DVAE tokens are ordered
It might make more sense to have top tokens, then bottom tokens
with top tokens having different discretized values.
2021-08-05 07:07:17 -06:00