Commit graph

183 commits

Author SHA1 Message Date
James Betker 29c1d9e561
Merge pull request #97 from jnordberg/cpu-support
CPU support
2022-06-12 23:12:03 -06:00
Johan Nordberg de7c5ddec3 Typofix 2022-06-11 21:19:07 +09:00
Johan Nordberg fc4a31028a Expose batch size and device settings in CLI 2022-06-11 20:46:23 +09:00
Johan Nordberg b876a6b32c Allow running on CPU 2022-06-11 20:03:14 +09:00
James Betker a9e64e216d
Merge pull request #90 from MarcusLlewellyn/read_combine
read.py combines all candidates
2022-06-06 14:59:35 -06:00
Marcus Llewellyn 700978b777 Fixed silly lack of EOF blank line, indentation 2022-06-06 15:13:29 -05:00
Marcus Llewellyn 2477a4f763 read.py combines all candidates
If candidates where greater than 1 on in read.py, only the fist candidate clips would be combined. This adds a bit of code to make a combined file for every candidate.
2022-06-04 17:47:29 -05:00
James Betker 480f7e37d9 Also include voices in the manifest 2022-05-31 10:31:50 -06:00
James Betker 48fe3288fe Include data in manifest 2022-05-31 09:10:06 -06:00
James Betker 780d2ce313
Merge pull request #78 from jnordberg/cli-typo-fix
Typofix in CLI
2022-05-28 22:30:41 -06:00
Johan Nordberg b73d46e811 Typofix 2022-05-29 04:26:11 +00:00
James Betker 68c1580f94
Merge pull request #74 from jnordberg/improved-cli
Add CLI tool
2022-05-28 21:33:53 -06:00
Johan Nordberg d8f98c07b4 Remove some assumptions about working directory
This allows cli tool to run when not standing in repository dir
2022-05-29 01:10:19 +00:00
James Betker 870b2d2fc2
Merge pull request #70 from jnordberg/sentence-split-improve
Improve sentence boundary detection
2022-05-28 11:03:43 -06:00
Johan Nordberg 9f6ae0f0b3 Add tortoise_cli.py 2022-05-28 05:25:23 +00:00
Johan Nordberg 561ae9a31e Typofix 2022-05-28 01:29:34 +00:00
Johan Nordberg 6a71d90316 Improve splitting on text that has many quotes 2022-05-28 01:22:21 +00:00
Johan Nordberg f199d6b85c Add riding hood test
Also fix a bug discovered by the test that would seek past the text end if it ended in a boundary
2022-05-27 23:08:53 +00:00
Johan Nordberg b294f0217f Improve sentence boundary detection 2022-05-27 05:58:09 +00:00
James Betker 3f7386d442
Merge pull request #68 from space-pope/fix-default-arg
avoid mutable default in aligner
2022-05-26 15:59:43 -06:00
Josh Ziegler 5b0e50eaa6
avoid mutable default in aligner 2022-05-26 16:20:09 -04:00
James Betker f56f3d5468 Fix import issue for CVVP 2022-05-26 08:44:20 -06:00
James Betker 3acca1445a
Merge pull request #64 from jnordberg/revive-cvvp
Revive CVVP model
2022-05-25 15:59:09 -06:00
Johan Nordberg b681fa9d11 Skip CLVP if cvvp_amount is 1
Also fixes formatting bug in log message
2022-05-25 11:12:53 +00:00
Johan Nordberg a52e3026ba Revive CVVP model 2022-05-25 10:22:50 +00:00
James Betker 7f9f1dbfc3 Fix bug 2022-05-22 05:50:26 -06:00
James Betker e118785aaf Support combining voices in do_tts 2022-05-22 05:28:15 -06:00
James Betker e882484c4a Update read.py to support multiple candidates 2022-05-22 05:26:01 -06:00
James Betker 8feb18b03f Merge remote-tracking branch 'origin/main' 2022-05-22 05:13:50 -06:00
James Betker 12a767c7f5 Commit comparisons with naturalspeech
This is the first TTS engine I've seen come along that has comparable performance
to Tortoise, though what has been released is pretty sparse on actual results. Still,
it's an interesting comparison.
2022-05-22 05:13:08 -06:00
James Betker eae0414f94
Merge pull request #58 from kwibjo/main
Update README.md
2022-05-21 10:41:55 -06:00
Jai Mu 5bff5dd819
Update README.md
Useless update but it was bothering me.
2022-05-22 00:56:06 +09:30
James Betker b98860552a
Merge pull request #57 from wavymulder/main
Updated train_lescault voices
2022-05-19 15:56:47 -06:00
Tristan Drake cdc138a3df Updated lescault voices 2022-05-19 17:39:25 -04:00
James Betker f4bd9c4dd0 Fix faulty merge 2022-05-19 10:37:57 -06:00
James Betker 1a8c9f741a Merge remote-tracking branch 'origin/main'
# Conflicts:
#	tortoise/read.py
2022-05-19 10:34:54 -06:00
James Betker 6d3157ebff Remove faulty 3rd example for train_mouse 2022-05-19 10:30:02 -06:00
James Betker 550874cbec Update broken train_empire voice 2022-05-19 10:26:46 -06:00
James Betker 2ba8d5bf97 Update requirements to specify version of transformers 2022-05-19 10:22:04 -06:00
James Betker 4641933d74
Merge pull request #55 from jnordberg/models-dir
Make models dir configurable
2022-05-19 09:51:21 -06:00
Johan Nordberg e34ffca8fb Allow passing additional voice directories when loading voices 2022-05-19 21:02:11 +09:00
Johan Nordberg 20220893af Allow setting models path from environment variable 2022-05-19 21:02:09 +09:00
James Betker 8139afd0e5 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 -06:00
James Betker 5d5aacc38c v2.4 2022-05-17 12:15:13 -06:00
James Betker aef86d21bf Add a way to get deterministic behavior from tortoise and add debug states for reporting 2022-05-17 12:11:18 -06:00
James Betker 9eac62598a Merge remote-tracking branch 'origin/main' 2022-05-17 11:22:40 -06:00
James Betker 24612f81c2 Add chapter 1 of GoT for read.py demos 2022-05-17 11:21:57 -06:00
James Betker 160963b105 Add conditioning latent example 2022-05-17 11:21:37 -06:00
James Betker b5fc8f198b
Merge pull request #49 from faad3/main
Fix bug in load_voices in audio.py
2022-05-17 11:20:44 -06:00
Danila Berezin dc3d7b1667
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 +03:00