Commit Graph

431 Commits

Author SHA1 Message Date
ZDisket 3f657d8ede add train, check notebook 2023-04-03 02:53:29 -04:00
ZDisket 4aa96d4697 Add inference notebooks 2023-04-03 02:53:29 -04:00
ZDisket e928e6b44a Add Tacotron2-CAC
- Tacotron2 based on https://github.com/keonlee9420/Comprehensive-Tacotron2
- Removed DeepSpeaker and Tensorflow dependency
- Added ARPA function
- Replaced guided attention loss with Convolutional Attention Consistency
2023-04-03 02:53:29 -04:00
ZDisket 5d78edd6b5 add this random stuff 2023-04-03 02:53:29 -04:00
Paul Sajna a9d643488b fix bugs introduced during slicing 2023-03-25 22:41:53 -07:00
Paul Sajna 572400ea85 update to so-vits-svc-fork repo 81551ce9c6fb7924d184c3c5a4cf9035168b28d2, add Dockerfile, reduce memory usage, remove unnecessary deps, use dio instead of parselmouth or crepe 2023-03-21 22:37:01 -07:00
ArEnSc af65e49da6 Got subchunking for audio lower than 15 seconds to be chunked a bit further then cross faded. 2023-03-21 21:10:55 -04:00
Brandon Thomas 8bac589838 fix vocoder paths 2023-03-21 05:53:07 -04:00
Brandon Thomas fc27fb26c7 Fix other script issues 2023-03-21 05:45:17 -04:00
Brandon Thomas 548ce49535 Fixes to inference script to match Rust 2023-03-21 05:35:30 -04:00
Brandon Thomas 85d9b7afec New entry point for subprocess/CLI-based inference 2023-03-21 03:58:36 -04:00
Brandon Thomas 89a7055c35 Update requirements, doc 2023-03-13 07:12:44 -04:00
Brandon Thomas b7ec3a2269 add so-vits-svc @ f22819cb8718ead5e50dea4fdbd05195c72fb1a8 2023-03-13 04:54:54 -04:00
Brandon Thomas 0082747d3c Try to suppress github scrollbar 2023-03-13 04:30:40 -04:00
Brandon Thomas cabd6ca6f7 ascii art 2023-03-13 04:29:45 -04:00
Brandon Thomas c4ec6ffc08 Update README. Root-level readme is going to go out of date
Since the root readme can't give us much information on each model,
we'll just add some ASCII art.
2023-03-13 04:26:27 -04:00
Brandon Thomas 9fe76017d4 update dockerfile to work locally 2023-03-13 03:59:24 -04:00
Brandon Thomas 9e011e9863 Move dockerfile and update build script 2023-03-13 01:48:03 -04:00
Brandon Thomas 9abfd9cda3 move irrelevant directories (we may delete them soon) 2023-03-13 01:44:54 -04:00
Brandon Thomas 1d6df5b68e Move our early TT2 into a subdirectory as we prepare to add more models 2023-03-13 01:43:02 -04:00
Brandon Thomas b5355de94e Add support for Ozzy's mel multiplier constant 2023-03-11 01:18:19 -05:00
Brandon Thomas 51199e8a6c readme update 2023-01-18 03:09:24 -05:00
Brandon Thomas 7adfe9978a README update 2023-01-18 03:08:40 -05:00
Brandon Thomas a108e4e410 End all sentences with punctuation. also Include some forgotten files 2023-01-12 04:19:11 -05:00
Brandon Thomas ca28449b1b Titles for check commands (did I test this? no?) 2023-01-12 03:41:14 -05:00
Brandon Thomas e3cc57979f Model check script 2022-12-16 05:21:09 -05:00
Brandon Thomas b1dca3ba63 Fix docker image to run on my system's host CUDA version 2022-12-12 20:54:11 -05:00
Brandon Thomas 3f0f94d92e better debugging, add gpu info, fix ffmpeg bug with -y 2022-12-12 19:40:37 -05:00
Brandon Thomas aa195675c0 Dockerfile for softvc 2022-12-12 19:28:07 -05:00
Brandon Thomas f6236dccca Truncate input audio 2022-12-12 17:42:46 -05:00
Brandon Thomas 0b9b7f7c4d Calculate wav metadata 2022-12-11 21:35:09 -05:00
Brandon Thomas 1220c7c0cd Inference cleanup, gitignore additions, etc. 2022-12-11 20:48:16 -05:00
Brandon Thomas 910641cde9 Working inference 2022-12-07 21:59:20 -05:00
Brandon Thomas 6281ebb454 SoftVC training notebook; training patch 2022-12-07 21:41:47 -05:00
Brandon Thomas 4837def3c2 WIP inference 2022-12-07 21:34:00 -05:00
Brandon Thomas 899d81efcc requirements.txt 2022-12-07 20:20:18 -05:00
Brandon Thomas 3bffd5996a Wav Samples, gitignore 2022-12-07 20:19:22 -05:00
Brandon Thomas 8f2a815d7d Add models for voice conversion 2022-12-07 19:59:01 -05:00
Brandon Thomas 99a9ccf3d8 move labels 2022-11-27 16:20:22 -05:00
Brandon Thomas 7115423a9e Dockerfile description, ignores, start script (local dev) 2022-11-27 16:10:38 -05:00
Brandon Thomas c7a880924f Add max_decoder_steps, streamline Dockerfile 2022-11-17 21:38:14 -05:00
Brandon Thomas 5163650b86 Move model code from Rust monorepo to improve Rust compile times
This will need work done to support w2l.
2022-11-13 17:49:37 -05:00
Brandon Thomas f738b88f9b Command line script to check HifiGan model validity 2022-08-07 20:11:54 -04:00
Brandon Thomas 79cb27a1f2 Fix dockerfile 2022-07-27 06:34:37 -04:00
Brandon Thomas eae5fbbc0c Merge pull request #6 from storytold/echelon-enable-spanish-espeak
Echelon enable spanish espeak
2022-07-27 06:24:04 -04:00
Brandon Thomas 19cf2bb285 Make use of the Spanish Espeak pipeline 2022-07-27 06:21:51 -04:00
Brandon Thomas 44f15c7a65 update dockerignore to skip local dev venv 2022-07-27 03:48:41 -04:00
Brandon Thomas 166cbbf5c8 Merge pull request #5 from storytold/espeak_phonemizer
Espeak phonemizer pipeline for spanish (and also english)
2022-07-15 05:58:10 -04:00
Brandon Thomas e7fcc23c3e Fix dockerfile escaping 2022-07-15 00:17:17 -04:00
Brandon Thomas d9114f0f28 Log request completion 2022-07-15 00:14:52 -04:00