mrq
/
tortoise-tts
4
6
Fork 15
Code Issues 9 Pull Requests 1 Packages Projects Releases Wiki Activity
332 Commits
2 Branches
0 Tags
378 MiB
Commit Graph

332 Commits (main)
 

Author SHA1 Message Date
James Betker a159a1ff53 Merge remote-tracking branch 'origin/main' 2022-05-22 05:13:50 +07:00
James Betker c343a7c8d4 Merge pull request #58 from kwibjo/main 
Update README.md
 2022-05-21 10:41:55 +07:00
Jai Mu dc5b296636 Update README.md 
Useless update but it was bothering me.
 2022-05-22 00:56:06 +07:00
James Betker d96d55a8b4 Fix faulty merge 2022-05-19 10:37:57 +07:00
James Betker a1c131bde9 Merge remote-tracking branch 'origin/main' 
# Conflicts:
#	tortoise/read.py
 2022-05-19 10:34:54 +07:00
James Betker 2c0e49e6a2 Update requirements to specify version of transformers 2022-05-19 10:22:04 +07:00
James Betker aa2a769075 Merge pull request #55 from jnordberg/models-dir 
Make models dir configurable
 2022-05-19 09:51:21 +07:00
Johan Nordberg b4fa8c86b9 Allow passing additional voice directories when loading voices 2022-05-19 21:02:11 +07:00
Johan Nordberg 00730d2786 Allow setting models path from environment variable 2022-05-19 21:02:09 +07:00
James Betker 8fdf516e62 Remove CVVP 
After training a similar model for a different purpose, I realized that
this model is faulty: the contrastive loss it uses only pays attention
to high-frequency details which do not contribute meaningfully to
output quality. I validated this by comparing a no-CVVP output with
a baseline using tts-scores and found no differences.
 2022-05-17 12:21:25 +07:00
James Betker 849db260ba v2.4 2022-05-17 12:15:13 +07:00
James Betker a1ae84c49d Add a way to get deterministic behavior from tortoise and add debug states for reporting 2022-05-17 12:11:18 +07:00
James Betker 93d0ce60d3 Merge remote-tracking branch 'origin/main' 2022-05-17 11:22:40 +07:00
James Betker 5d611aff8c Add chapter 1 of GoT for read.py demos 2022-05-17 11:21:57 +07:00
James Betker fcc7b16677 Merge pull request #49 from faad3/main 
Fix bug in load_voices in audio.py
 2022-05-17 11:20:44 +07:00
Danila Berezin ef5fb5f5fc Fix bug in load_voices in audio.py 
The read.py script did not work with pth latents, so I fix bug in audio.py. It seems that in the elif statement, instead of voice, voices should be clip, clips. And torch stack doesn't work with tuples, so I had to split this operation.
 2022-05-17 18:34:54 +07:00
James Betker e0329de2c2 Merge pull request #42 from jnordberg/main 
Improve sentence splitting
 2022-05-14 08:52:46 +07:00
James Betker 0570034eda Automatically pick batch size based on available GPU memory 2022-05-13 10:30:02 +07:00
Johan Nordberg a8fa71b82d Improve sentence splitting 2022-05-13 11:02:17 +07:00
James Betker 556172281d Release notes for 2.3 2022-05-12 20:26:24 +07:00
James Betker b3b36c0041 update model paths (including clvp2!) 2022-05-12 20:18:11 +07:00
James Betker f5ebd14d09 Add error message 2022-05-12 20:15:40 +07:00
James Betker c4a5a23985 add eval script for testing 2022-05-12 20:15:22 +07:00
James Betker 44a4419348 CLVP2! 2022-05-12 13:23:03 +07:00
James Betker fc7b308e3b Add support for multiple output candidates in do_tts. 2022-05-12 11:25:35 +07:00
James Betker 33d4226a7d read.py: allow user-specified splits 2022-05-12 11:24:55 +07:00
James Betker 5c60c5d4f2 Merge pull request #36 from e0xextazy/main 
Optimizing graphics card memory
 2022-05-11 21:46:16 +07:00
Mark Baushenko cc38333249 Optimizing graphics card memory 
During inference it does not store gradients, which take up most of the video memory
 2022-05-11 16:35:11 +07:00
James Betker ea8c825ee0 update requirements to (hopefully) provide better compatibility 
man python deps are garbage.....
 2022-05-10 23:42:37 +07:00
James Betker ef2ce3fd05 Update README with suggestions for windows installation 2022-05-08 20:44:44 +07:00
James Betker e4e9523900 re-enable redaction 2022-05-06 09:36:42 +07:00
James Betker 9151650559 temporarily disable redaction 2022-05-06 09:06:20 +07:00
James Betker e18428166d v2.2 2022-05-06 00:11:10 +07:00
James Betker 4704eb1cef Update readme with prompt engineering 2022-05-03 21:32:06 +07:00
James Betker b11f6ddd60 Enable redaction by default 2022-05-03 21:21:52 +07:00
James Betker 53cb3299d4 change quality presets 2022-05-03 21:01:26 +07:00
James Betker e23e6f6696 Use librosa for loading mp3s 2022-05-03 20:44:31 +07:00
James Betker e981898de7 Update notebook 2022-05-02 21:57:19 +07:00
James Betker dc0390ade1 Remove entmax dep 2022-05-02 21:43:14 +07:00
James Betker 12acac6f77 Fix default output path 2022-05-02 21:37:39 +07:00
James Betker 022d330300 k I think this works.. 2022-05-02 21:31:31 +07:00
James Betker 958b939b64 Add setup 2022-05-02 21:24:34 +07:00
James Betker 19f38f454f Update README and update to version 2.1 2022-05-02 21:02:29 +07:00
James Betker 00e84bbd86 fix paths 2022-05-02 20:56:28 +07:00
James Betker e4e8ebfc55 getting ready for 2.1 release 2022-05-02 20:20:50 +07:00
James Betker 5663e98904 misc fixes 2022-05-02 18:00:57 +07:00
James Betker e00606a601 Fix bug with k>1 2022-05-02 18:00:22 +07:00
James Betker ccf16f978e more fixes 2022-05-02 16:44:47 +07:00
James Betker 4836e1f792 fix warning 2022-05-02 16:36:02 +07:00
James Betker ee24d3ee4b Support totally random voices (and make fixes to previous changes) 2022-05-02 15:40:03 +07:00