Commit Graph

1413 Commits

Author SHA1 Message Date
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