Kinan Martin
a6f60de9dd
add utility file for creating subsets of mls english. must be fixed to make dev and test splits have matching sizes to reazonspeech
2025-06-06 11:44:27 +09:00
Kinan Martin
052fcc3218
add utility file for updating the storage_path of cutsets for use in the multilingual training recipe directory structure
2025-06-06 11:42:08 +09:00
Kinan Martin
6255ba5cb2
fix decode script data module usage
2025-06-06 11:29:29 +09:00
Kinan Martin
ce894a7ba2
Combined updates. Changed BBPE path structure, changed dataset path structure, added script to update cutset paths. WIP
2025-06-04 10:12:39 +09:00
Kinan Martin
1f11ba4d28
use huggingface_hub library to download mls_english
2025-05-22 09:15:12 +09:00
Kinan Martin
f3f04fa626
switch mls_english clone from https to ssh
2025-05-21 10:25:47 +09:00
Kinan Martin
e6615df4eb
fix stage 5 output pathing
2025-05-15 09:11:40 +09:00
Kinan Martin
daff070d68
restore version of mls_english compute_fbank_mls_english.py and prepare.sh from commit 547f5c5
2025-05-15 07:24:26 +09:00
Kinan Martin
e34f2dbb2a
merge change to remove bilingual param with new multidataset_datamodule
2025-05-14 08:51:11 +09:00
Kinan Martin
eb5004880f
deprecate params.bilingual=0, replace ReazonSpeechAsrDataModule for MultiDatasetAsrDataModule, not tested yet
2025-05-14 08:41:03 +09:00
Bailey Hirota
7ef1811063
remove bilingual tag from train.py
2025-05-14 08:37:44 +09:00
Bailey Hirota
b2df5bbb83
Revert "add fbank"
...
This reverts commit ba603e0a0a514056ec6d32677053c41743a1a5dd.
2025-05-13 09:43:17 +09:00
Bailey Hirota
82bd37cacd
add fbank
2025-05-13 09:43:05 +09:00
Kinan Martin
21d1bf73bb
new version of multi_ja_en prepare.sh script which swaps Librispeech for MLS English
2025-05-09 10:57:41 +09:00
Kinan Martin
547f5c5cfb
optimize with num_jobs on save_audios
2025-05-02 07:22:38 +09:00
Kinan Martin
88249f0eb4
fix stage 2 and 3
2025-05-01 08:15:07 +09:00
Kinan Martin
90326c1f43
fix validation manifest name
2025-05-01 08:05:42 +09:00
Kinan Martin
dbe270ba94
adjusted prepare.sh to only calculate fbank and manifest together; adjust datamodule to load from manifest files
2025-04-30 10:06:13 +09:00
Kinan Martin
cf425173af
move compute_fbank_mls_english.py, add validate_manifest.py, add shared symlink to librispeech
2025-04-24 09:39:54 +09:00
Kinan Martin
4f743993ef
instead of on-the-fly features, precompute fbank and manifests in prepare.sh
2025-04-23 10:13:15 +09:00
Kinan Martin
4e2a4fdcd8
readme
2025-04-16 08:13:59 +09:00
Kinan Martin
bb6d672b54
pre-commit hooks
2025-04-16 08:05:05 +09:00
Kinan Martin
e69e1c04b2
separate transcript prep stage from bpe train stage
2025-04-16 07:15:25 +09:00
Kinan Martin
6e81d9aa5b
symlink copied files to librispeech recipe dir
2025-04-16 07:11:25 +09:00
Kinan Martin
0e868049a6
Merge branch 'k2-fsa:master' into mls_english_clean
2025-04-15 17:52:18 -04:00
Kinan Martin
cf8e9a8a1c
cleaned-up version of recipe
2025-04-15 10:19:51 +09:00
Kinan Martin
a4be3cb3db
replace file
2025-04-14 08:27:50 +09:00
Kinan Martin
1e9bb87305
change default path
2025-04-11 10:30:08 +09:00
Kinan Martin
3eeadd0f3a
update prepare.sh, fix asr_datamodule.py
2025-04-11 10:29:27 +09:00
math345
64c5364085
Fix bug: When resuming training from a checkpoint, model_avg was not assigned, resulting in a None error. ( #1914 )
2025-04-10 11:37:28 +08:00
Fangjun Kuang
300a821f58
Fix aishell training ( #1916 )
2025-04-10 10:30:37 +08:00
Fangjun Kuang
171cf8c9fe
Avoid redundant computation in PiecewiseLinear. ( #1915 )
2025-04-09 11:52:37 +08:00
Kinan Martin
93766fc24f
WIP v0 MLS English recipe
2025-04-09 10:22:20 +09:00
Wei Kang
86bd16d496
[KWS]Remove graph compiler ( #1905 )
2025-04-02 22:10:06 +08:00
Fangjun Kuang
db9fb8ad31
Add scripts to export streaming zipformer(v1) to RKNN ( #1882 )
2025-02-27 17:10:58 +08:00
Yuekai Zhang
2ba665abca
Add F5-TTS with semantic token training results ( #1880 )
...
* add cosy token
* update inference code
* add extract cosy token
* update results
* add requirements.txt
* update readme
---------
Co-authored-by: yuekaiz <yuekaiz@h20-7.cm.cluster>
Co-authored-by: yuekaiz <yuekaiz@mgmt1-login.cm.cluster>
2025-02-24 13:58:47 +08:00
Machiko Bailey
da597ad782
Update RESULTS.md ( #1873 )
2025-02-04 09:04:25 +08:00
Machiko Bailey
0855b0338a
Merge japanese-to-english multilingual branch ( #1860 )
...
* add streaming support to reazonresearch
* update README for streaming
* Update RESULTS.md
* add onnx decode
---------
Co-authored-by: root <root@KDA03.cm.cluster>
Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
Co-authored-by: root <root@KDA01.cm.cluster>
Co-authored-by: zr_jin <peter.jin.cn@gmail.com>
2025-02-04 01:33:09 +08:00
Yuekai Zhang
dd5d7e358b
F5-TTS Training Recipe for WenetSpeech4TTS ( #1846 )
...
* add f5
* add infer
* add dit
* add README
* update pretrained checkpoint usage
---------
Co-authored-by: yuekaiz <yuekaiz@h20-5.cm.cluster>
Co-authored-by: yuekaiz <yuekaiz@l20-3.cm.cluster>
Co-authored-by: yuekaiz <yuekaiz@h20-6.cm.cluster>
Co-authored-by: zr_jin <peter.jin.cn@gmail.com>
2025-01-27 16:33:02 +08:00
zr_jin
39c466e802
Update shared ( #1868 )
2025-01-21 11:04:11 +08:00
zr_jin
79074ef0d4
removed the erroneous ‘’continual'' implementation ( #1865 )
2025-01-16 20:51:28 +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
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
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
Fangjun Kuang
bfffda5afb
Add MatchaTTS for the Chinese dataset Baker ( #1849 )
2024-12-31 17:17:05 +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
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
d4d4f281ec
Revert "Replace deprecated pytorch methods ( #1814 )" ( #1841 )
...
This reverts commit 3e4da5f78160d3dba3bdf97968bd7ceb8c11631f.
2024-12-18 16:49:57 +08:00
