unknown
|
2cdafa429a
|
...
|
2025-02-13 08:40:28 -08:00 |
|
unknown
|
7cc3f86f3b
|
remove DOCKER_UTILS
|
2025-02-13 08:35:36 -08:00 |
|
unknown
|
c9c92905d6
|
v25.2.0rc4
|
2025-02-06 18:56:59 -08:00 |
|
unknown
|
53eae7c605
|
added flac and more audio format processing!
|
2025-01-18 15:13:57 -08:00 |
|
unknown
|
b91b6e8852
|
lock coqui-tts version. wrap up batch directory option
|
2025-01-17 18:03:06 -08:00 |
|
unknown
|
c18c491952
|
finalizing batch directory option
|
2025-01-16 17:35:01 -08:00 |
|
unknown
|
1c66f2bb64
|
first step adding batch directory, still not working
|
2025-01-16 09:54:04 -08:00 |
|
unknown
|
d1ec9a1a05
|
various fixes
|
2025-01-16 07:49:00 -08:00 |
|
unknown
|
bc718ad860
|
replace DockerFile and compose
|
2025-01-15 15:34:48 -08:00 |
|
unknown
|
0a50fadc0e
|
v2.1.0rc3
|
2025-01-15 06:35:09 -08:00 |
|
unknown
|
c7fc4bf8c8
|
fixed 400 tokens bug, get_chapters() optimization
|
2025-01-08 14:21:34 -08:00 |
|
unknown
|
5457ecb788
|
typos fixes, added default settings
|
2025-01-07 06:06:07 -08:00 |
|
unknown
|
823fbec426
|
v2.1.0rc1
|
2025-01-06 03:19:26 -08:00 |
|
unknown
|
e9f4740ea7
|
various fixes
|
2024-12-24 06:06:41 -08:00 |
|
unknown
|
663483f165
|
replace 22khz voices to 16khz for fairseq, fixed tts loading and cache
|
2024-12-22 21:02:20 -08:00 |
|
unknown
|
101ca1692d
|
added fine tuned models in conf.py, renamed some
|
2024-12-22 05:53:47 -08:00 |
|
unknown
|
1439306f06
|
BobRoss typo
|
2024-12-21 21:08:16 -08:00 |
|
unknown
|
20937ce1f2
|
fix conf inversion, added BobRoss in fine-tuned
|
2024-12-21 20:57:14 -08:00 |
|
unknown
|
bc38df7ac1
|
updated custom_model now managed by session, fixed various bugs
|
2024-12-21 15:45:47 -08:00 |
|
unknown
|
11b65800d9
|
added new options in conf.py, custom_model still in dev
|
2024-12-18 20:43:28 -08:00 |
|
unknown
|
61c32ce27a
|
fixed fine-tuned, custom modal upload back and working(?)
|
2024-12-16 21:13:43 -08:00 |
|
unknown
|
c5f555d0dd
|
fixed chapter combien audio bug. fine-tuned model cache still to solve
|
2024-12-14 21:05:56 -08:00 |
|
unknown
|
5af1c0d01a
|
implementation of fine-tuned and various fixes
|
2024-12-14 16:06:49 -08:00 |
|
unknown
|
1a374ce8fc
|
fix chapter audio and settences order, device gpu to cuda
|
2024-12-13 18:40:31 -08:00 |
|
unknown
|
25a07ad3c1
|
fix model loading, removed unused conf model options
|
2024-12-12 16:50:58 -08:00 |
|
unknown
|
0502e375cf
|
Multiprocessing, multithread, multiuser ready, various changes and fixes
|
2024-12-11 19:47:49 -08:00 |
|
unknown
|
3e819a3efa
|
double quotes to simple quotes normalization
|
2024-11-28 04:35:05 -08:00 |
|
unknown
|
ba52a2b5d7
|
regenerate test files, various bug fixes, new implementation
|
2024-11-27 20:27:51 -08:00 |
|
Drew Thomasson
|
80a9f568e8
|
Update conf.py update download link to the viet xtts model
|
2024-11-25 16:46:17 -05:00 |
|
Drew Thomasson
|
fa35a70b3a
|
Update conf.py fixed typo
|
2024-11-24 22:28:49 -05:00 |
|
unknown
|
36454c67ec
|
Merge branch 'v2.0' of https://github.com/ROBERT-MCDOWELL/ebook2audiobook into v2.0
|
2024-11-24 18:50:57 -08:00 |
|
unknown
|
aba6763a24
|
move test files to tests folder, recreate models folder
|
2024-11-24 18:48:06 -08:00 |
|
Drew Thomasson
|
a969e8d976
|
Updated link to xtts Model that supports Vietnamese
|
2024-11-24 19:16:47 -05:00 |
|
Drew Thomasson
|
f8626511eb
|
swapped with link to xtts v2.0.3 backup zip
|
2024-11-16 10:13:04 -08:00 |
|
Drew Thomasson
|
0e676491cf
|
Update conf.py added a unidic_path for future development
|
2024-11-16 09:44:23 -08:00 |
|
DrewThomasson
|
d6db2838d6
|
fixed comma typo
|
2024-11-16 03:37:02 -05:00 |
|
DrewThomasson
|
c51aef52ad
|
added dictionary for current fine-tuned xtts models
|
2024-11-16 03:31:22 -05:00 |
|
DrewThomasson
|
af7688107d
|
Now automatically downloads the base xtts model for you in the model dir to use :)
|
2024-11-16 02:20:46 -05:00 |
|
DrewThomasson
|
d6297a5aaf
|
Reverted multiple commits put them on the v2.0-auto-download-xtts-models branch
|
2024-11-15 22:29:47 -05:00 |
|
DrewThomasson
|
99f0886123
|
Now automatically downloads the base xtts model for you in the model dir to use :)
|
2024-11-15 18:43:01 -05:00 |
|
ROBERT-MCDOWELL
|
f24d8014dc
|
added conversion cancellation, improved theme, previous bug fixed
|
2024-11-07 04:07:15 +00:00 |
|
ROBERT-MCDOWELL
|
7bd9d52afe
|
renammed some vars to be more explicit, session reload first step
|
2024-11-03 22:45:40 +00:00 |
|
ROBERT-MCDOWELL
|
bee11e904b
|
fix windows calibre permissions
|
2024-11-03 14:38:23 +00:00 |
|
ROBERT-MCDOWELL
|
1f97b55809
|
.
|
2024-11-03 05:06:47 +00:00 |
|
ROBERT-MCDOWELL
|
63dc7c05a1
|
unidic last fixes
|
2024-11-03 04:28:51 +00:00 |
|
ROBERT-MCDOWELL
|
7a8bf42233
|
various fixes
|
2024-10-30 20:37:13 +00:00 |
|
ROBERT-MCDOWELL
|
37e730a913
|
various fixes, change models default path to ./models
|
2024-10-30 18:04:53 +00:00 |
|
ROBERT-MCDOWELL
|
c9ead76ed2
|
fixes windows paths
|
2024-10-29 19:09:10 +00:00 |
|
ROBERT-MCDOWELL
|
4051be2789
|
fix unidic, nltk, varioux other fixes
|
2024-10-29 03:55:38 +00:00 |
|
ROBERT-MCDOWELL
|
069ae0f5b8
|
removed install.*, ebook2audiobook.* are now the inst. and launcher
|
2024-10-27 03:09:22 +00:00 |
|