Yifan Yang
54d0a2b499
Merge branch 'k2-fsa:master' into dev/k2ssl
2025-01-11 15:28:03 +08:00
Han Zhu
ab91112909
Improve infinity-check ( #1862 )
...
1. Attach the inf-check hooks if the grad scale is getting too small.
2. Add try-catch to avoid OOM in the inf-check hooks.
3. Set warmup_start=0.1 to reduce chances of divergence
2025-01-09 15:05:38 +08:00
Yifan Yang
dcc4730219
Merge branch 'k2-fsa:master' into dev/k2ssl
2025-01-06 17:31:34 +08:00
Seonuk Kim
8d602806c3
Update conformer.py ( #1859 )
...
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
Swich -? Swish
2025-01-06 17:31:13 +08:00
Yifan Yang
ab44ac0f9e
Merge branch 'k2-fsa:master' into dev/k2ssl
2025-01-06 17:30:59 +08:00
Seonuk Kim
3b6d54007b
Update conformer.py ( #1857 )
...
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
* Update conformer.py
feedforward dimention -> feedforward dimension
2025-01-06 13:17:02 +08:00
Fangjun Kuang
3b263539cd
Publish MatchaTTS onnx models trained with LJSpeech to huggingface ( #1854 )
2025-01-02 15:54:34 +08:00
Yifan Yang
c64a9bac05
Merge branch 'k2-fsa:master' into dev/k2ssl
2025-01-01 19:22:05 +08:00
Fangjun Kuang
bfffda5afb
Add MatchaTTS for the Chinese dataset Baker ( #1849 )
2024-12-31 17:17:05 +08:00
Han Zhu
df46a3eaf9
Warn instead of raising exceptions in inf-check ( #1852 )
2024-12-31 16:52:06 +08:00
Yifan Yang
e8fa10e53a
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-12-31 09:09:45 +08:00
Yifan Yang
a2b0f6057c
Small fix ( #1853 )
2024-12-31 07:41:44 +08:00
Han Zhu
48088cb807
Refactor optimizer ( #1837 )
...
* Print indexes of largest grad
2024-12-30 15:30:02 +08:00
Han Zhu
57e9f2a8db
Add the "rms-sort" diagnostics ( #1851 )
2024-12-30 15:27:05 +08:00
Yifan Yang
01e2c2a566
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-12-22 10:30:21 +08:00
Fangjun Kuang
ad966fb81d
Minor fixes to the onnx inference script for ljspeech matcha-tts. ( #1838 )
2024-12-19 15:19:41 +08:00
Fangjun Kuang
92ed1708c0
Add torch 1.13 and 2.0 to CI tests ( #1840 )
2024-12-18 16:50:14 +08:00
Fangjun Kuang
d4d4f281ec
Revert "Replace deprecated pytorch methods ( #1814 )" ( #1841 )
...
This reverts commit 3e4da5f78160d3dba3bdf97968bd7ceb8c11631f.
2024-12-18 16:49:57 +08:00
Li Peng
3e4da5f781
Replace deprecated pytorch methods ( #1814 )
...
* Replace deprecated pytorch methods
- torch.cuda.amp.GradScaler(...) => torch.amp.GradScaler("cuda", ...)
- torch.cuda.amp.autocast(...) => torch.amp.autocast("cuda", ...)
* Replace `with autocast(...)` with `with autocast("cuda", ...)`
Co-authored-by: Li Peng <lipeng@unisound.ai>
2024-12-16 10:24:16 +08:00
Yifan Yang
ebd31daba4
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-12-14 13:24:40 +08:00
zr_jin
d475de5600
Merge pull request #1835 from JinZr/fix/matcha-minor
2024-12-11 19:03:19 +08:00
zr_jin
b7acf0f57b
minor fixes
2024-12-11 14:33:47 +08:00
zr_jin
a43480af47
fixed the not found python 3.8 env ( #1830 )
2024-12-10 11:15:49 +08:00
zr_jin
08caa1e4e5
minor fixes to the matcha recipe
2024-12-09 22:59:29 +08:00
zr_jin
32b7a449e7
removed unnecessary type check ( #1827 )
2024-12-08 17:36:08 +08:00
zr_jin
d33f678176
fixed the formatting issue of PR#1812 ( #1828 )
2024-12-08 16:37:24 +08:00
goddamnVincent
5c04f7bfb8
'try to fix 'compute_fbank_kespeech_splits.py: error: unrecognized arguments: --speed-perturb true'' ( #1812 )
2024-12-08 11:17:15 +08:00
zr_jin
1c4dd464a0
Performed end to end testing on the matcha recipe ( #1797 )
...
* minor fixes to the `ljspeech/matcha` recipe
2024-12-08 03:18:15 +08:00
zr_jin
6e6b022e41
performed end to end testing to the VALL-E recipe ( #1818 )
...
* added the missing ``visualize`` function
* minor fixes
2024-12-06 16:14:51 +08:00
Han Zhu
bdd0f85704
Fix the normalized_text in LibriTTS recipe ( #1825 )
2024-12-05 15:12:06 +08:00
zr_jin
a1ade8ecb7
fixed failed assertion in the xbmu_ambo31
recipe ( #1816 )
2024-11-29 16:36:02 +08:00
Han Zhu
18fa6a0fec
Fix LibriTTS prepare.sh ( #1815 )
2024-11-29 11:45:05 +08:00
Yifan Yang
6cda09860e
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-11-22 21:40:26 +08:00
Yuekai Zhang
cbe012d54c
Valle Recipe for WenetSpeech4TTS, LibriTTS, LibriTTS-R ( #1805 )
...
* add valle
* update readme
2024-11-22 11:18:01 +08:00
Yifan Yang
893fee43d4
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-11-04 22:46:11 +08:00
Yifan Yang
57451b0382
refactor ksponspeech recipe ( #1794 )
...
Co-authored-by: Your Name <>
2024-11-01 22:49:19 +08:00
zr_jin
66225fbe33
VITS recipe for LibriTTS corpus ( #1776 )
2024-11-01 15:33:13 +08:00
Yifan Yang
277b261e09
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-10-31 11:18:51 +08:00
Yifan Yang
119e1ce3e8
fix str2bool ( #1792 )
2024-10-31 09:54:12 +08:00
zr_jin
87cadfcd2e
fixed formatting issue ( #1791 )
...
* isort fixed formatting issue
2024-10-30 21:14:12 +08:00
Wei Kang
d513d456b8
Add prefix beam search and corresponding decoding methods ( #1786 )
...
* Add prefix beam search / shallow fussion / hotwords in librispeech ctc decode
* Add librispeech cr-ctc prefix beam search results
2024-10-30 10:14:34 +08:00
Fangjun Kuang
6c7863c2f8
Fix CI tests ( #1788 )
...
Use numpy<2.0
2024-10-29 22:26:25 +08:00
Fangjun Kuang
f23c8ce9dd
Fix CI test for gigaspeech ( #1787 )
2024-10-29 15:50:49 +08:00
Fangjun Kuang
516b4869b3
Add Matcha-TTS ( #1773 )
2024-10-29 15:04:04 +08:00
Your Name
1b89c6dac4
skipping batch counts hurts performance
2024-10-28 22:59:27 -07:00
Yifan Yang
d4b6cb09ad
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-10-28 12:19:52 +08:00
Fangjun Kuang
7e9eea6dc3
Add pretrained.py for SURT ( #1785 )
2024-10-28 11:53:11 +08:00
Fangjun Kuang
05f756390c
Avoid using lr from checkpoint. ( #1781 )
2024-10-28 00:59:04 +08:00
Yifan Yang
34957a6ff0
Merge branch 'k2-fsa:master' into dev/k2ssl
2024-10-24 15:43:43 +08:00
Your Name
ce72b34c30
update
2024-10-24 00:43:16 -07:00