mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-05 15:14:18 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,016 Commits 5 Branches 3 Tags
Commit Graph

1016 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
jinzr
94d1f4d1b4 docs fixed 2023-12-05 16:37:14 +08:00
jinzr
02f11c57f0 docs updated 2023-12-05 16:30:22 +08:00
jinzr
fddfd2466f Update test_onnx.py 2023-12-05 14:40:54 +08:00
jinzr
eb686b8da3 Update test_onnx.py 2023-12-05 14:38:35 +08:00
jinzr
8717043bdf updated requirements.txt 2023-12-05 13:29:53 +08:00
jinzr
64903abf77 Update test_onnx.py 2023-12-05 10:45:05 +08:00
jinzr
fefae1f8df Update export-onnx.py 2023-12-05 09:24:40 +08:00
jinzr
e401a724ac Update export-onnx.py 2023-12-05 08:53:20 +08:00
jinzr
d4c830823c updated docs 2023-12-04 11:59:16 +08:00
jinzr
0cb2b12adb Update infer.py 2023-12-04 10:01:38 +08:00
jinzr
e2cadd8380 Update infer.py 2023-12-04 10:00:51 +08:00
jinzr
ddecda0c9b Update infer.py 2023-12-04 09:58:00 +08:00
jinzr
52fe6f9bfd Update requirements_tts.txt 
added version constraints
 2023-12-04 09:47:50 +08:00
jinzr
79c8f95f3d Create requirements_tts.txt 2023-12-03 16:02:12 +08:00
jinzr
002cda8f54 minor adjustments 2023-12-01 02:04:11 +08:00
jinzr
8b9ab595c1 Update prepare.sh 2023-12-01 01:48:47 +08:00
jinzr
998b9d8aa4 created symlinks 2023-12-01 00:16:58 +08:00
jinzr
9931694455 removed redundant files 2023-12-01 00:16:00 +08:00
jinzr
0f051f5518 Create monotonic_align 2023-12-01 00:12:46 +08:00
jinzr
ee718f1da1 removed redundant files 2023-12-01 00:12:35 +08:00
jinzr
b7efcbf154 Update infer.py 2023-12-01 00:08:23 +08:00
jinzr
cf7ad8131d fixed formatting issue 2023-12-01 00:08:16 +08:00
jinzr
8c75259723 Update train.py 2023-11-30 23:09:11 +08:00
jinzr
26d387c41f Update train.py 2023-11-30 23:06:20 +08:00
jinzr
4f697c4caa Update train.py 2023-11-30 23:06:03 +08:00
jinzr
48c90df9c9 Update train.py 2023-11-30 23:04:11 +08:00
jinzr
0ef3da24c1 Update train.py 2023-11-30 22:50:29 +08:00
jinzr
cbf8b2d36c Update train.py 2023-11-30 22:47:59 +08:00
jinzr
615a5e8d46 Update tts_datamodule.py 2023-11-30 22:41:46 +08:00
jinzr
523635cf77 Update train.py 2023-11-30 22:37:40 +08:00
jinzr
2eb06451ee Update train.py 2023-11-30 22:32:07 +08:00
jinzr
0e7f0a4ee9 updated 2023-11-30 22:11:44 +08:00
jinzr
100e622c18 Update prepare.sh 2023-11-30 16:37:48 +08:00
jinzr
b99f2f3996 Update prepare_tokens_vctk.py 2023-11-30 15:44:18 +08:00
jinzr
a0d93368f8 Update prepare_tokens_vctk.py 2023-11-30 15:30:07 +08:00
jinzr
adf2fc06a5 Update prepare_tokens_vctk.py 2023-11-30 15:27:39 +08:00
zr_jin
9c753c5ca6
Merge branch 'k2-fsa:master' into dev/vits-vctk2 2023-11-30 02:56:13 +08:00
Zengwei Yao
0622dea30d
Add a TTS recipe VITS on LJSpeech dataset (#1372) 
* first commit

* replace phonimizer with g2p

* use Conformer as text encoder

* modify training script, clean codes

* rename directory

* convert text to tokens in data preparation stage

* fix tts_datamodule.py

* support onnx export and testing the exported onnx model

* add doc

* add README.md

* fix style
 2023-11-29 21:28:38 +08:00
jinzr
c0b214c8bc Create shared 2023-11-29 16:11:58 +08:00
jinzr
617721dfc3 minor updates 2023-11-29 16:07:44 +08:00
zr_jin
ae67f75e9c
a bilingual recipe similar to the multi-zh_hans (#1265) 2023-11-26 10:04:15 +08:00
Wei Kang
238b45bea8
Libriheavy recipe (zipformer) (#1261) 
* initial commit for libriheavy

* Data prepare pipeline

* Fix train.py

* Fix decode.py

* Add results

* minor fixes

* black

* black

* Incorporate PR https://github.com/k2-fsa/icefall/pull/1269

---------

Co-authored-by: zr_jin <peter.jin.cn@gmail.com>
 2023-11-23 01:22:57 +08:00
Wei Kang
11d816d174
Add cumstomized score for hotwords (#1385) 
* add custom score for each hotword

* Add more comments

* Fix deocde

* fix style

* minor fixes
 2023-11-18 18:47:55 +08:00
Fangjun Kuang
666d69b20d
Rename train2.py to avoid confusion (#1386) 2023-11-17 18:12:59 +08:00
Karel Vesely
59c943878f
add the voxpopuli recipe (#1374) 
* add the `voxpopuli` recipe

- this is the data preparation
- there is no ASR training and no results

* update the PR#1374 (feedback from @csukuangfj)

- fixing .py headers and docstrings
- removing BUT specific parts of `prepare.sh`
- adding assert `num_jobs >= num_workers` to `compute_fbank.py`
- narrowing list of languages
  (let's limit to ASR sets with transcripts for now)
- added links to `README.md`
- extending `text_from_manifest.py`
 2023-11-16 14:38:31 +08:00
zr_jin
431048a1c7
Merge branch 'k2-fsa:master' into dev/vits-vctk2 2023-11-13 14:44:20 +08:00
zr_jin
6d275ddf9f
fixed broken softlinks (#1381) 
* removed broken softlinks

* fixed dependencies

* fixed file permission
 2023-11-10 14:45:16 +08:00
jinzr
3c1b465d37 isort formatted 2023-11-10 11:04:46 +08:00
lishaojie
1b2e99d374
add the pruned_transducer_stateless7_streaming recipe for commonvoice (#1018) 
* add the pruned_transducer_stateless7_streaming recipe for commonvoice

* fix the symlinks

* Update RESULTS.md
 2023-11-09 22:07:28 +08:00
JinZr
269cc3b66a init 2023-11-06 15:28:54 +08:00