deepgeek/Matcha-TTS
2
0
Fork 0
mirror of https://github.com/shivammehta25/Matcha-TTS.git synced 2026-02-04 17:59:19 +08:00
Code Issues Packages Projects Releases Wiki Activity
118 Commits 6 Branches 7 Tags
pre-commit-ci-update-config
Commit Graph

70 Commits

Author SHA1 Message Date
pre-commit-ci[bot]
66178aea04 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2026-01-19 22:11:39 +00:00
Shivam Mehta
108906c603 Merge pull request #121 from jimregan/english-data 
ljspeech/hificaptain from #99
 2024-12-02 09:02:41 -06:00
Jim O’Regan
8e5f98476e Fix a typo 2024-12-02 15:21:31 +01:00
Jim O'Regan
7e499df0b2 ljspeech/hificaptain from #99 2024-12-02 11:01:04 +00:00
Shivam Mehta
0735e653fc Merge pull request #103 from jimregan/mmconv-cleaner 
add a cleaner for IPA data (pre-phonetised)
 2024-11-13 22:15:47 -08:00
Shivam Mehta
f9843cfca4 Merge pull request #101 from jimregan/pylint 
Make pylint happy
 2024-11-13 22:13:36 -08:00
Shivam Mehta
289ef51578 Fixing thhe usage of denoiser_strength from the command line. 2024-11-14 06:55:51 +01:00
Shivam Mehta
7a65f83b17 Updating the version 2024-11-14 06:42:06 +01:00
Shivam Mehta
7275764a48 Fixing espeak not removing brackets in some cases 2024-11-14 06:39:58 +01:00
Jim O'Regan
863bfbdd8b rename method, it's more generic than the previous name suggested 2024-10-03 18:51:47 +00:00
Jim O'Regan
4bc541705a add a cleaner for the mmconv data 
Different versions of espeak represent things differently, it seems
(also, there are some distinctions none of our speakers make, so
normalising those away reduces perplexity a tiny amount).
 2024-10-03 17:18:58 +00:00
pre-commit-ci[bot]
a3fea22988 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2024-10-02 14:31:11 +00:00
Jim O'Regan
d56f40765c disable consider-using-from-import instead (missed one) 2024-10-02 14:30:18 +00:00
Jim O'Regan
b0ba920dc1 disable consider-using-from-import instead 2024-10-02 14:29:06 +00:00
Jim O'Regan
a220f283e3 disable consider-using-generator 2024-10-02 13:57:12 +00:00
Jim O'Regan
1df73ef43e disable global-variable-not-assigned 2024-10-02 13:55:44 +00:00
Jim O'Regan
404b045b65 add dummy exception (W0719) 2024-10-02 13:51:17 +00:00
Jim O'Regan
7cfae6bed4 add dummy exception (W0719) 2024-10-02 13:49:47 +00:00
Jim O'Regan
a83fd29829 C0209 2024-10-02 13:45:27 +00:00
Jim O'Regan
8b1284993a W1514 + R1732 2024-10-02 13:31:57 +00:00
Jim O'Regan
0000f93021 R1732 + W1514 2024-10-02 13:25:02 +00:00
pre-commit-ci[bot]
c2569a1018 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2024-10-02 13:21:37 +00:00
Jim O'Regan
bd058a68f7 R0402 2024-10-02 13:21:00 +00:00
Jim O'Regan
362ba2dce7 C0209 2024-10-02 08:38:28 +00:00
Shivam Mehta
77804265f8 removing diffuser versioning 2024-08-09 18:28:56 +02:00
Shivam Mehta
de910380bc Fixing batched synthesis for multispeaker model 2024-05-27 13:40:02 +02:00
Shivam Mehta
aa496aa13f Adding the possibility to train with durations 2024-05-27 13:24:21 +02:00
Shivam Mehta
4b39f6cad0 Adding the possibility of get durations out of pretrained model 2024-05-24 11:34:51 +02:00
Shivam Mehta
fb7b954de5 Updating different url for hifigan as well 2024-01-12 11:21:51 +00:00
Shivam Mehta
5a52a67cf7 Version bump 2024-01-12 11:11:41 +00:00
Shivam Mehta
39cbd85236 Using Wget for new ckpt downloadsA 2024-01-12 11:09:25 +00:00
Shivam Mehta
95ec24b599 Version bump 2024-01-12 10:48:52 +00:00
Shivam Mehta
19bea20928 Merge branch 'main' into dev 2024-01-12 10:37:17 +00:00
Shivam Mehta
8268360674 Update download urls 2024-01-12 10:32:59 +00:00
Shivam Mehta
0ed9290c31 Logging global step while training 2023-12-06 10:39:54 +00:00
Shivam Mehta
f39ee6cf3b Changing while to for for more readibility 2023-12-05 12:10:52 +00:00
Shivam Mehta
6e71dc8b8f adding prior loss as a configuration 2023-12-05 09:57:37 +00:00
Shivam Mehta
a18db17330 Removing the option for configuring prior loss, the durations predicted are not so good then 2023-12-04 10:12:39 +00:00
Shivam Mehta
263d5c4d4e Adding piper phonemizer with different dataset 2023-12-01 12:06:26 +00:00
Shivam Mehta
df896301ca Minor changes moving option to disable prior loss in config 2023-12-01 10:44:49 +00:00
Shivam Mehta
1ead4303f3 Version Bump 2023-09-29 14:50:46 +00:00
mush42
336dd20d5b Use torch.onnx.is_in_onnx_export() instead of torch.jit.is_scripting() since the former is dedicated to this use case. 2023-09-26 15:28:15 +02:00
mush42
01c99161c4 - Fixed several bugs. Thanks @shivammehta25 for the suggestions 2023-09-26 14:21:17 +02:00
mush42
2c21a0edac Fixed an error encountered when loading the vocoder during export. 2023-09-24 20:28:59 +02:00
mush42
1b204ed42c ONNX export and inference. Complete and tested implmentation. 2023-09-24 01:57:35 +02:00
Shivam Mehta
d373e9a5b1 Bumping it to an increased version 2023-09-21 13:43:20 +00:00
Shivam Mehta
f12be190a4 ADding video teaser to readme 2023-09-21 13:41:21 +00:00
Shivam Mehta
a49af19f48 Another version bump because I am new to twine 2023-09-21 13:25:40 +00:00
Shivam Mehta
309739b7cc Version bump 2023-09-21 13:20:17 +00:00
Shivam Mehta
0aaabf90c4 Minor UI fixes 2023-09-21 13:18:32 +00:00