James Betker
6996dfd9d5
asr_hf2: add independent position embedders
2021-12-26 15:17:24 -07:00
James Betker
5b5cbc057c
Work checkpoint for gpt asr hf2
2021-12-26 10:29:12 -07:00
James Betker
cd89e6b42e
Initialize our embeddings the same way GPT-2 initializes theirs.
2021-12-26 00:20:30 -07:00
James Betker
8d01f7685c
Get rid of absolute positional embeddings in unifiedvoice
2021-12-26 00:10:24 -07:00
James Betker
6700f8851d
moar verbosity
2021-12-25 23:23:21 -07:00
James Betker
8acf3b3097
Better dimensional asserting
2021-12-25 23:18:25 -07:00
James Betker
e959541494
Add position embeddings back into unified_voice
...
I think this may be the solution behind the days problems.
2021-12-25 23:10:56 -07:00
James Betker
64cb4a92db
Support adamw_zero
2021-12-25 21:32:01 -07:00
James Betker
776a7abfcc
Support torch DDP _set_static_graph
2021-12-25 21:20:06 -07:00
James Betker
746392f35c
Fix DS
2021-12-25 15:28:59 -07:00
James Betker
736c2626ee
build in character tokenizer
2021-12-25 15:21:01 -07:00
James Betker
b595c62893
One way decoder for decoding from mel codes
2021-12-25 12:18:00 -07:00
James Betker
ab9cafa572
Make tokenization configs more configurable
2021-12-25 12:17:50 -07:00
James Betker
52410fd9d9
256-bpe tokenizer
2021-12-25 08:52:08 -07:00
James Betker
8e26400ce2
Add inference for unified gpt
2021-12-24 13:27:06 -07:00
James Betker
ead2a74bf0
Add debug_failures flag
2021-12-23 16:12:16 -07:00
James Betker
9677f7084c
dataset mod
2021-12-23 15:21:30 -07:00
James Betker
8b19c37409
UnifiedGptVoice!
2021-12-23 15:20:26 -07:00
James Betker
5bc9772cb0
grand: support validation mode
2021-12-23 15:03:20 -07:00
James Betker
e55d949855
GrandConjoinedDataset
2021-12-23 14:32:33 -07:00
James Betker
b9de8a8eda
More fixes
2021-12-22 19:21:29 -07:00
James Betker
191e0130ee
Another fix
2021-12-22 18:30:50 -07:00
James Betker
6c6daa5795
Build a bigger, better tokenizer
2021-12-22 17:46:18 -07:00
James Betker
c737632eae
Train and use a bespoke tokenizer
2021-12-22 15:06:14 -07:00
James Betker
66bc60aeff
Re-add start_text_token
2021-12-22 14:10:35 -07:00
James Betker
a9629f7022
Try out using the GPT tokenizer rather than nv_tacotron
...
This results in a significant compression of the text domain, I'm curious what the
effect on speech quality will be.
2021-12-22 14:03:18 -07:00
James Betker
ced81a760b
restore nv_tacotron
2021-12-22 13:48:53 -07:00
James Betker
7bf4f9f580
duplicate nvtacotron
2021-12-22 13:48:30 -07:00
James Betker
7ae7d423af
VoiceCLIP model
2021-12-22 13:44:11 -07:00
James Betker
09f7f3e615
Remove obsolete lucidrains DALLE stuff, re-create it in a dedicated folder
2021-12-22 13:44:02 -07:00
James Betker
a42b94ab72
gpt_tts_hf inference fixes
2021-12-22 13:22:15 -07:00
James Betker
48e3ee9a5b
Shuffle conditioning inputs along the positional axis to reduce fitting on prosody and other positional information
...
The mels should still retain some short-range positional information the model can use
for tone and frequencies, for example.
2021-12-20 19:05:56 -07:00
James Betker
53858b2055
Fix gpt_tts_hf inference
2021-12-20 17:45:26 -07:00
James Betker
712d746e9b
gpt_tts: format conditioning inputs more for contextual voice clues and less for prosidy
...
also support single conditional inputs
2021-12-19 17:42:29 -07:00
James Betker
c813befd53
Remove dedicated positioning embeddings
2021-12-19 09:01:31 -07:00
James Betker
b4ddcd7111
More inference improvements
2021-12-19 09:01:19 -07:00
James Betker
f9c45d70f0
Fix mel terminator
2021-12-18 17:18:06 -07:00
James Betker
937045cb63
Fixes
2021-12-18 16:45:38 -07:00
James Betker
9b9f7ea61b
GptTtsHf: Make the input/target placement easier to reason about
2021-12-17 10:24:14 -07:00
James Betker
2fb4213a3e
More lossy fixes
2021-12-17 10:01:42 -07:00
James Betker
dee34f096c
Add use_gpt_tts script
2021-12-16 23:28:54 -07:00
James Betker
9e8a9bf6ca
Various fixes to gpt_tts_hf
2021-12-16 23:28:44 -07:00
James Betker
62c8ed9a29
move speech utils
2021-12-16 20:47:37 -07:00
James Betker
e7957e4897
Make loss accumulator for logs accumulate better
2021-12-12 22:23:17 -07:00
James Betker
4f8c4d130c
gpt_tts_hf: pad mel tokens with an <end_of_sequence> token.
2021-12-12 20:04:50 -07:00
James Betker
76f86c0e47
gaussian_diffusion: support fp16
2021-12-12 19:52:21 -07:00
James Betker
aa7cfd1edf
Add support for mel norms across the channel dim
2021-12-12 19:52:08 -07:00
James Betker
8917c02a4d
gpt_tts_hf inference first pass
2021-12-12 19:51:44 -07:00
James Betker
63bf135b93
Support norms
2021-12-11 08:30:49 -07:00
James Betker
959979086d
fix
2021-12-11 08:18:00 -07:00
James Betker
5a664aa56e
misc
2021-12-11 08:17:26 -07:00
James Betker
d610540ce5
mel norm computation script
2021-12-11 08:16:50 -07:00
James Betker
306274245b
Also do dynamic range compression across mel
2021-12-10 20:06:24 -07:00
James Betker
faf55684b8
Use slaney norm in the mel filterbank computation
2021-12-10 20:04:52 -07:00
James Betker
b2d8fbcfc0
build a better speech synthesis toolset
2021-12-09 22:59:56 -07:00
James Betker
32cfcf3684
Turn off optimization in find_faulty_files
2021-12-09 09:02:09 -07:00
James Betker
a66a2bf91b
Update find_faulty_files
2021-12-09 09:00:00 -07:00
James Betker
9191201f05
asd
2021-12-07 09:55:39 -07:00
James Betker
ef15a39841
fix gdi bug?
2021-12-07 09:53:48 -07:00
James Betker
6ccff3f49f
Record codes more often
2021-12-07 09:22:45 -07:00
James Betker
d0b2f931bf
Add feature to diffusion vocoder where the spectrogram conditioning layers can be re-trained apart from the rest of the model
2021-12-07 09:22:30 -07:00
James Betker
662920bde3
Log codes when simply fetching codebook_indices
2021-12-06 09:21:43 -07:00
James Betker
380a5d5475
gdi..
2021-12-03 08:53:09 -07:00
James Betker
101a01f744
Fix dvae codes issue
2021-12-02 23:28:36 -07:00
James Betker
31fc693a8a
dafsdf
2021-12-02 22:55:36 -07:00
James Betker
040d998922
maasd
2021-12-02 22:53:48 -07:00
James Betker
cc10e7e7e8
Add tsv loader
2021-12-02 22:43:07 -07:00
James Betker
702607556d
nv_tacotron_dataset: allow it to load conditioning signals
2021-12-02 22:14:44 -07:00
James Betker
07b0124712
GptTtsHf!
2021-12-02 21:48:42 -07:00
James Betker
85542ec547
One last fix for gpt_asr_hf2
2021-12-02 21:19:28 -07:00
James Betker
68e9db12b5
Add interleaving and direct injectors
2021-12-02 21:04:49 -07:00
James Betker
04454ee63a
Add evaluation logic for gpt_asr_hf2
2021-12-02 21:04:36 -07:00
James Betker
47fe032a3d
Try to make diffusion validator more reproducible
2021-11-24 09:38:10 -07:00
James Betker
5956eb757c
ffffff
2021-11-24 00:19:47 -07:00
James Betker
f1ed0588e3
another fix
2021-11-24 00:11:21 -07:00
James Betker
7a3c4a4fc6
Fix lr quantizer decode
2021-11-24 00:01:26 -07:00
James Betker
3f6ecfe0db
q fix
2021-11-23 23:50:27 -07:00
James Betker
d9747fe623
Integrate with lr_quantizer
2021-11-23 19:48:22 -07:00
James Betker
82d0e7720e
Add choke to lucidrains_dvae
2021-11-23 18:53:37 -07:00
James Betker
934395d4b8
A few fixes for gpt_asr_hf2
2021-11-23 09:29:29 -07:00
James Betker
3b5c3d85d8
Allow specification of wandb run name
2021-11-22 17:31:29 -07:00
James Betker
01e635168b
whoops
2021-11-22 17:24:13 -07:00
James Betker
973f47c525
misc nonfunctional
2021-11-22 17:16:39 -07:00
James Betker
3125ca38f5
Further wandb logs
2021-11-22 16:40:19 -07:00
James Betker
19c80bf7a7
Improve wandb logging
2021-11-22 16:40:05 -07:00
James Betker
0604060580
Finish up mods for next version of GptAsrHf
2021-11-20 21:33:49 -07:00
James Betker
14f3155ec4
misc
2021-11-20 17:45:14 -07:00
James Betker
687e0746b3
Add Torch-derived MelSpectrogramInjector
2021-11-18 20:02:45 -07:00
James Betker
555b7e52ad
Add rev2 of GptAsrHf
2021-11-18 20:02:24 -07:00
James Betker
c30a38cdf1
Undo baseline GDI changes
2021-11-18 20:02:09 -07:00
James Betker
1287915f3c
Fix dvae test failure
2021-11-18 00:58:36 -07:00
James Betker
019acfa4c5
Allow flat dvae
2021-11-18 00:53:42 -07:00
James Betker
f3db41f125
Fix code logging
2021-11-18 00:34:37 -07:00
James Betker
f36bab95dd
Audio resample injector
2021-11-10 20:06:33 -07:00
James Betker
79367f753d
Fix error & add nonfinite warning
2021-11-09 23:58:41 -07:00
James Betker
5d5558893a
Merge remote-tracking branch 'origin/master'
2021-11-08 20:10:49 -07:00
James Betker
d43f25cc20
Update losses
2021-11-08 20:10:07 -07:00
James Betker
c584320cf3
Fix gpt_asr_hf distillation
2021-11-07 21:53:21 -07:00
James Betker
9b3c3b1227
use sets instead of list ops
2021-11-07 20:45:57 -07:00
James Betker
722d3dbdc2
f
2021-11-07 18:52:05 -07:00
James Betker
18b1de9b2c
Add exclusion_lists to unsupervised_audio_dataset
2021-11-07 18:46:47 -07:00
James Betker
9b693b0a54
Fixes to filter_clips_hifreq
2021-11-07 18:42:22 -07:00
James Betker
a367ea3fda
Add script for computing attention for gpt_asr
2021-11-07 18:42:06 -07:00
James Betker
3c0f2fbb21
Add filtration script for finding resampled clips (or phone calls)
2021-11-07 14:16:11 -07:00
James Betker
756b4dad09
Working gpt_asr_hf inference - and it's a beast!
2021-11-06 21:47:15 -06:00
James Betker
596a62fe01
Apply fix to gpt_asr_hf and prep it for inference
...
Fix is that we were predicting two characters in advance, not next character
2021-11-04 10:09:24 -06:00
James Betker
fd14746bf8
badtimes
2021-11-03 00:33:38 -06:00
James Betker
2fa80486de
tacotron_dataset: recover gracefully
2021-11-03 00:31:50 -06:00
James Betker
af51d00dee
Load wav files from voxpopuli instead of oggs
2021-11-02 09:32:26 -06:00
James Betker
3b65241b6b
Get rid of printing grad names (didn't work very well..)
2021-11-01 18:44:05 -06:00
James Betker
993bd52d42
Add spec_augment injector
2021-11-01 18:43:11 -06:00
James Betker
4cff774b0e
Reduce complexity of the encoder for gpt_asr_hf
2021-11-01 17:02:28 -06:00
James Betker
da55ca0438
gpt_asr using the huggingfaces transformer
2021-11-01 17:00:22 -06:00
James Betker
ee9b199d2b
Build in capacity to revert & resume networks that encounter a NaN
...
I'm increasingly seeing issues where something like this can be useful. In many (most?)
cases it's just a waste of compute, though. Still, better than a cold computer for a whole
night.
2021-11-01 16:14:59 -06:00
James Betker
87364b890f
Add custom clip_grad_norm that prints out the param names in error.
2021-11-01 11:12:20 -06:00
James Betker
f7d0901ce6
Decouple MEL from nv_tacotron_dataset
2021-10-31 15:01:38 -06:00
James Betker
b8b268b5f6
Misc
2021-10-31 14:29:23 -06:00
James Betker
b404a3b747
Revert recent changes to extr
2021-10-30 20:48:06 -06:00
James Betker
83cccef9d8
Condition on full signal
2021-10-30 19:58:34 -06:00
James Betker
e9dc37f19c
Mod trainer to copy config file into experiments root
2021-10-30 17:00:24 -06:00
James Betker
36ed28913a
Fix two scripts
2021-10-30 17:00:06 -06:00
James Betker
df45a9dec2
Fix inference mode for lucidrains_gpt
2021-10-30 16:59:18 -06:00
James Betker
466b9fbcaa
classify
2021-10-29 20:22:40 -06:00
James Betker
92fe8b4dd9
ffffpt2
2021-10-29 17:29:49 -06:00
James Betker
95ca88efce
Fix feedforward
2021-10-29 17:27:51 -06:00
James Betker
b476516340
Check in backing changes (which may have broken something?)
2021-10-29 17:22:33 -06:00
James Betker
986fc9628d
Check in GPT with new inference methods (but not the backing code..)
2021-10-29 17:21:40 -06:00
James Betker
0822792d79
Fix options.py bug
2021-10-29 14:47:31 -06:00
James Betker
928e7026c2
Mod STFT injector to be specifiable
2021-10-28 22:34:12 -06:00
James Betker
579f0a70ee
Move UnsupervisedAudioDataset to use my new mp3 loader
2021-10-28 22:33:12 -06:00
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
James Betker
4017236ba9
Fix up inference for gpt_tts
2021-08-05 06:46:30 -06:00
James Betker
5037220ac7
Mods to support contrastive learning on audio files
2021-08-05 05:57:04 -06:00
James Betker
341f28dd82
It works!
2021-08-04 20:07:51 -06:00
James Betker
36c7c1fbdb
Fix training flow for NEXT TOKEN prediction instead of same token prediction
...
doh
2021-08-04 10:28:09 -06:00
James Betker
d9936df363
Add gpt_tts dataset and implement inference
...
- Adds a script which preprocesses quantized mels given a DVAE
- Adds a dataset which can consume preprocessed qmels
- Reworks GPT TTS to consume the outputs of that dataset (removes logic to add padding and start/end tokens)
- Adds inference to gpt_tts
2021-08-04 00:44:04 -06:00
James Betker
4c98b9703f
Get dalle-style TTS to "work"
2021-08-03 21:08:27 -06:00
James Betker
2814307eee
Alterations to support VQVAE on mel spectrograms
2021-08-01 07:54:21 -06:00
James Betker
965f6e6b52
Fixes to weight_decay in adamw
2021-07-31 15:58:41 -06:00
James Betker
0c9e75bc69
Improvements to GptTts
2021-07-31 15:57:57 -06:00
James Betker
31ee9ae262
Checkin
2021-07-30 23:07:35 -06:00
James Betker
dadc54795c
Add gpt_tts
2021-07-27 20:33:30 -06:00
James Betker
398185e109
More work on wave-diffusion
2021-07-27 05:36:17 -06:00
James Betker
49e3b310ea
Allow audio sample rate interpolation for faster training
2021-07-26 17:44:06 -06:00
James Betker
96e90e7047
Add support for a gaussian-diffusion-based wave tacotron
2021-07-26 16:27:31 -06:00
James Betker
97d7cbbc34
Additional work for audio xformer (which doesnt really do a great job)
2021-07-23 10:58:14 -06:00
James Betker
2325e7a88c
Allow inference for vqvae
2021-07-20 10:40:05 -06:00
James Betker
d81386c1be
Mods to support vqvae in audio mode (1d)
2021-07-20 08:36:46 -06:00
James Betker
5584cfcc7a
tacotron2 work
2021-07-14 21:41:57 -06:00
James Betker
fe0c699ced
Various fixes
2021-07-14 00:08:42 -06:00
James Betker
be2745f42d
Add waveglow & inference capabilities to audio generator
2021-07-08 23:07:36 -06:00
James Betker
1ff434218e
tacotron2, ready for prime time!
2021-07-08 22:13:44 -06:00
James Betker
86fd3ad7fd
Initial checkin of nvidia tacotron model & dataset
...
These two are tested, full support for training to come.
2021-07-06 11:11:35 -06:00
James Betker
3801d5d55e
diffusion surfin'
2021-07-06 09:36:52 -06:00
James Betker
afa41f1804
Allow hq color jittering and corruptions that are not included in the corruption factor
2021-06-30 09:44:46 -06:00
James Betker
6fd16ea9c8
Add meta-anomaly detection, colorjitter augmentation
2021-06-29 13:41:55 -06:00
James Betker
46e9f62be0
Add unet with latent guide
...
This is a diffusion network that uses both a LQ image
and a reference sample HQ image that is compressed into
a latent vector to perform upsampling
The hope is that we can steer the upsampling network
with sample images.
2021-06-26 11:02:58 -06:00
James Betker
0ded106562
Merge remote-tracking branch 'origin/master'
2021-06-25 13:16:28 -06:00
James Betker
a57ed8e960
Various mods to support better jpeg image filtering
2021-06-25 13:16:15 -06:00
James Betker
61e7ca39cd
Update image_folder_dataset.py
2021-06-25 11:48:31 -06:00
James Betker
a0ef07ddb8
Create unet_latent_guide.py
2021-06-25 11:25:14 -06:00
James Betker
e7890dc0ba
Misc fixes for diffusion nets
2021-06-21 10:38:07 -06:00
James Betker
8e3a33e001
Fix a bug where non-rank-0 is computing FID before all images are saved.
2021-06-16 16:27:09 -06:00
James Betker
68cbbed886
Add some cool diffusion testing scripts
2021-06-16 16:26:36 -06:00
James Betker
ae8de0cb9d
fid saving images across all rank fix
2021-06-15 10:31:07 -06:00
James Betker
6a75bd0777
Another fix
2021-06-14 09:51:44 -06:00
James Betker
54bff35171
Fix issue where eval was not being used by all ddp processes
2021-06-14 09:50:04 -06:00
James Betker
60079a1572
Fix saver in distributed mode
2021-06-14 09:41:06 -06:00
James Betker
545f2db170
Distributed FID dataset across processes
2021-06-14 09:33:44 -06:00
James Betker
6b32c87dcb
Try to make diffusion fid more deterministic
2021-06-14 09:27:43 -06:00
James Betker
5b4f86293f
Add FID evaluator for diffusion models
2021-06-14 09:14:30 -06:00
James Betker
9cfe840872
Attempt to fix syncing multiple times when doing gradient accumulation
2021-06-13 14:30:30 -06:00
James Betker
1cd75dfd33
Fix ddp bug
2021-06-13 10:25:23 -06:00
James Betker
3e3ad7825f
Add support for training an EMA network alongside the main networks
2021-06-12 21:01:41 -06:00
James Betker
696f320820
Get rid of feature networks
2021-06-11 20:50:07 -06:00
James Betker
65c474eecf
Various changes to fix testing
2021-06-11 15:31:10 -06:00
James Betker
220f11a5e4
Half channel sizes in cifar_resnet
2021-06-09 17:06:37 -06:00
James Betker
aea12e1b9c
Fix cat eval hack
2021-06-09 17:05:11 -06:00
James Betker
9b5f4abb91
Add fade in for hard switch
2021-06-07 18:15:09 -06:00
James Betker
108c5d829c
Fix dropout norm
2021-06-07 16:13:23 -06:00
James Betker
438217094c
Also debug distribution of switch
2021-06-07 15:36:07 -06:00
James Betker
44b09e5f20
Amplify dropout rate
2021-06-07 15:20:53 -06:00
James Betker
f0d4eb9182
Fixor
2021-06-07 11:58:36 -06:00
James Betker
c456a60466
Another go at fixing nan
2021-06-07 11:51:43 -06:00
James Betker
1c574c5bd1
Attempt to fix nan
2021-06-07 11:43:42 -06:00
James Betker
eda796985b
Try out dropout norm
2021-06-07 11:33:33 -06:00
James Betker
6c6e82406e
Pass a corruption factor through the dataset into the upsampling network
...
The intuition is this will help guide the network to make better informed decisions
about how it performs upsampling based on how it perceives the underlying content.
(I'm giving up on letting networks detect their own quality - I'm not convinced it is
actually feasible)
2021-06-07 09:13:54 -06:00
James Betker
2ad2b56438
Don't do wandb except on rank 0
2021-06-06 16:52:07 -06:00
James Betker
7c5478bc2c
Formatting issue with gdi
2021-06-06 16:35:37 -06:00
James Betker
061dbcd458
Another fix to anorm
2021-06-06 15:09:49 -06:00
James Betker
9a6991e461
Fix switch norm average
2021-06-06 15:04:28 -06:00
James Betker
57e1a6a0f2
cifar: add hard routing
...
Also mods switched_routing to support non-pixular inputs
2021-06-06 14:53:43 -06:00
James Betker
692e9c417b
Support diffusion unet
2021-06-06 13:57:22 -06:00
James Betker
a0158ebc69
Simplify cifar resnet further for faster training
2021-06-06 10:02:24 -06:00
James Betker
75567a9814
Only head norm removed
2021-06-05 23:29:11 -06:00
James Betker
65d0376b90
Re-add normalization at the tail of the RRDB
2021-06-05 23:04:05 -06:00
James Betker
184e887122
Remove rrdb normalization
2021-06-05 21:39:19 -06:00
James Betker
f5e75602b9
Add regular attention to cifar_resnet
2021-06-05 21:34:07 -06:00
James Betker
16cd92acd5
hack
2021-06-05 14:23:41 -06:00
James Betker
af52751d6b
Fix device error
2021-06-05 14:21:32 -06:00
James Betker
5f0cc65f3b
Register branched resnet properly
2021-06-05 14:19:03 -06:00
