marcoyang
|
7ead73f746
|
update readme
|
2024-03-14 18:23:16 +08:00 |
|
marcoyang
|
390f01653f
|
resolve conflict
|
2024-03-14 18:22:36 +08:00 |
|
marcoyang
|
cf92d40a9d
|
update README
|
2024-03-14 18:19:06 +08:00 |
|
marcoyang
|
c7180b9869
|
add missing file
|
2024-03-14 17:19:09 +08:00 |
|
marcoyang
|
af04e7d7be
|
support export and merge weight of a LoRA zipformer
|
2024-03-14 17:18:51 +08:00 |
|
marcoyang
|
c0924f0a2f
|
register the weight and bias
|
2024-03-14 12:20:45 +08:00 |
|
Xiaoyu Yang
|
f28c05f4f5
|
Documentation for adapter fine-tuning (#1545)
|
2024-03-14 12:18:49 +08:00 |
|
zr_jin
|
eb132da00d
|
additional instruction for the grad_scale is too small error (#1550)
|
2024-03-14 11:33:49 +08:00 |
|
Fangjun Kuang
|
15bd9a841e
|
add CI for ljspeech (#1548)
|
2024-03-13 17:39:01 +08:00 |
|
Fangjun Kuang
|
d406b41cbd
|
Doc: Add page for installing piper-phonemize (#1547)
|
2024-03-13 11:01:18 +08:00 |
|
zr_jin
|
c3f6f28116
|
Zipformer recipe for Cantonese dataset MDCC (#1537)
* init commit
* Create README.md
* handle code switching cases
* misc. fixes
* added manifest statistics
* init commit for the zipformer recipe
* added scripts for exporting model
* added RESULTS.md
* added scripts for streaming related stuff
* doc str fixed
|
2024-03-13 10:01:28 +08:00 |
|
Fangjun Kuang
|
81f518ea7c
|
Support different tts model types. (#1541)
|
2024-03-12 22:29:21 +08:00 |
|
BannerWang
|
959906e9dc
|
Correct alimeeting download link (#1544)
Co-authored-by: BannerWang <banner.wang@upblocks.io>
|
2024-03-12 12:44:09 +08:00 |
|
jimmy1984xu
|
e472fa6840
|
fix CutMix init parameter (#1543)
Co-authored-by: jimmyxu <jimmyxu@upblocks.io>
|
2024-03-11 18:37:26 +08:00 |
|
marcoyang
|
6806810666
|
bug fix
|
2024-03-11 12:18:03 +08:00 |
|
marcoyang
|
3492d9415c
|
add lora version of ActivationDropouAndLinear; currently a simple version
|
2024-03-11 12:02:35 +08:00 |
|
marcoyang
|
bb8f6b0ef7
|
add lora to the in_proj of the feedforward module
|
2024-03-11 10:45:36 +08:00 |
|
Fangjun Kuang
|
60986c3ac1
|
Fix default value for --context-size in icefall. (#1538)
|
2024-03-08 20:47:13 +08:00 |
|
zr_jin
|
ae61bd4090
|
Minor fixes for the commonvoice recipe (#1534)
* init commit
* fix for issue https://github.com/k2-fsa/icefall/issues/1531
* minor fixes
|
2024-03-08 11:01:11 +08:00 |
|
marcoyang
|
5272a71ec9
|
also add lora in SelfAttention (for the value proj)
|
2024-03-08 10:40:18 +08:00 |
|
Yuekai Zhang
|
5df24c1685
|
Whisper large fine-tuning on wenetspeech, mutli-hans-zh (#1483)
* add whisper fbank for wenetspeech
* add whisper fbank for other dataset
* add str to bool
* add decode for wenetspeech
* add requirments.txt
* add original model decode with 30s
* test feature extractor speed
* add aishell2 feat
* change compute feature batch
* fix overwrite
* fix executor
* regression
* add kaldifeatwhisper fbank
* fix io issue
* parallel jobs
* use multi machines
* add wenetspeech fine-tune scripts
* add monkey patch codes
* remove useless file
* fix subsampling factor
* fix too long audios
* add remove long short
* fix whisper version to support multi batch beam
* decode all wav files
* remove utterance more than 30s in test_net
* only test net
* using soft links
* add kespeech whisper feats
* fix index error
* add manifests for whisper
* change to licomchunky writer
* add missing option
* decrease cpu usage
* add speed perturb for kespeech
* fix kespeech speed perturb
* add dataset
* load checkpoint from specific path
* add speechio
* add speechio results
---------
Co-authored-by: zr_jin <peter.jin.cn@gmail.com>
|
2024-03-07 19:04:27 +08:00 |
|
zr_jin
|
cdb3fb5675
|
add text norm script for pl (#1532)
|
2024-03-07 18:47:29 +08:00 |
|
marcoyang
|
9bc1ad87b4
|
add script for decoding
|
2024-03-07 15:42:33 +08:00 |
|
marcoyang
|
a56034799b
|
first version of lora, could just run
|
2024-03-07 12:28:39 +08:00 |
|
marcoyang
|
87b19c0bd2
|
add finetune.py
|
2024-03-06 17:06:40 +08:00 |
|
marcoyang
|
3b3256a426
|
add files again
|
2024-03-06 17:02:21 +08:00 |
|
marcoyang
|
3c92bdb5fa
|
add more files
|
2024-03-06 12:28:20 +08:00 |
|
zr_jin
|
335a9962de
|
Fixed formatting issue of PR #1528 (#1530)
|
2024-03-06 08:43:45 +08:00 |
|
marcoyang
|
86a51e0771
|
initial commit
|
2024-03-05 18:30:43 +08:00 |
|
Rezakh20
|
ff430b465f
|
Add num_features to train.py for training WSASR (#1528)
|
2024-03-05 16:40:30 +08:00 |
|
zr_jin
|
242002e0bd
|
Strengthened style constraints (#1527)
|
2024-03-04 23:28:04 +08:00 |
|
Fangjun Kuang
|
29b195a42e
|
Update export-onnx.py for vits to support sherpa-onnx. (#1524)
|
2024-03-01 19:53:58 +08:00 |
|
zr_jin
|
58610b1bf6
|
Provides README.md for TTS recipes (#1491)
* Update README.md
|
2024-02-29 17:31:28 +08:00 |
|
Fangjun Kuang
|
2f102eb989
|
Add CUDA docker image for torch 2.2.1 (#1521)
|
2024-02-29 11:41:18 +08:00 |
|
Xiaoyu Yang
|
7e2b561bbf
|
Add recipe for fine-tuning Zipformer with adapter (#1512)
|
2024-02-29 10:57:38 +08:00 |
|
Zengwei Yao
|
d89f4ea149
|
Use piper_phonemize as text tokenizer in ljspeech recipe (#1511)
* use piper_phonemize as text tokenizer in ljspeech recipe
* modify usage of tokenizer in vits/train.py
* update docs
|
2024-02-29 10:13:22 +08:00 |
|
Fangjun Kuang
|
291d06056c
|
Support torch 2.2.1 for cpu docker. (#1516)
|
2024-02-23 14:24:13 +08:00 |
|
Xiaoyu Yang
|
2483b8b4da
|
Zipformer recipe for SPGISpeech (#1449)
|
2024-02-22 15:53:19 +08:00 |
|
Wei Kang
|
819bb45539
|
Add pypinyin to requirements (#1515)
|
2024-02-22 15:50:11 +08:00 |
|
Wei Kang
|
aac7df064a
|
Recipes for open vocabulary keyword spotting (#1428)
* English recipe on gigaspeech; Chinese recipe on wenetspeech
|
2024-02-22 15:31:20 +08:00 |
|
Xiaoyu Yang
|
13daf73468
|
docs for finetune zipformer (#1509)
|
2024-02-21 18:06:27 +08:00 |
|
Wei Kang
|
c19b414778
|
Update docker (adding pypinyin (#1513)
Update docker (adding pypinyin)
|
2024-02-21 08:04:16 +08:00 |
|
zr_jin
|
027302c902
|
minor fix for param. names (#1495)
|
2024-02-20 14:38:51 +08:00 |
|
Karel Vesely
|
e59fa38e86
|
docs: minor fixes of LM rescoring texts (#1498)
|
2024-02-20 10:40:15 +08:00 |
|
Zengwei Yao
|
b3e2044068
|
minor fix of vits/tokenizer.py (#1504)
* minor fix of vits/tokenizer.py
|
2024-02-19 19:33:32 +08:00 |
|
zr_jin
|
db4d66c0e3
|
Fixed softlink for ljspeech recipe (#1503)
|
2024-02-19 16:13:09 +08:00 |
|
Fangjun Kuang
|
7eb360d0d5
|
Fix cpu docker images for torch 2.2.0 (#1502)
|
2024-02-18 20:32:40 +08:00 |
|
Fangjun Kuang
|
17688476e5
|
Provider docker images for torch 2.2.0 (#1501)
|
2024-02-18 14:56:04 +08:00 |
|
Fangjun Kuang
|
06b356a610
|
Update cpu docker images to support torch 2.2.0 (#1499)
|
2024-02-18 12:05:38 +08:00 |
|
safarisadegh
|
d9ae8c02a0
|
Update README.md (#1497)
|
2024-02-09 15:05:01 +08:00 |
|