Commit Graph

  • b336ccfe8d update audio api in apps #2414 Yang Zhou 2022-09-18 12:43:55 +0800
  • e3298c79ce Merge branch 'develop' into u2_export Hui Zhang 2022-09-19 14:15:23 +0000
  • 260752aa2a using forward_attention_decoder Hui Zhang 2022-09-19 14:10:16 +0000
  • 522b32d50c add finetune demos, test=doc TianYuan 2022-09-19 12:40:00 +0000
  • 68bd85a6b8
    Merge branch 'PaddlePaddle:develop' into develop WongLaw 2022-09-19 19:56:51 +0800
  • 5e714ecb4a
    [doc]update api docs (#2406) TianYuan 2022-09-19 18:35:08 +0800
  • 750e0bdddd fix coding style && mv audio docs #2405 YangZhou 2022-09-19 06:49:15 +0000
  • 357c31e2b8 fix docstring of VITS, test=doc #2406 TianYuan 2022-09-19 03:45:05 +0000
  • 78469519b6 update apt docs, test=doc TianYuan 2022-09-19 03:15:51 +0000
  • d697130585 Merge branch 'hongliang0909' of https://github.com/david-95/PaddleSpeech into hongliang0909 david.95 2022-09-19 09:35:11 +0800
  • e66d1b7d96 update audio api in app #2403 Yang Zhou 2022-09-18 12:43:55 +0800
  • 57463b64e0
    Merge pull request #2400 from zh794390558/audio_dev_merge YangZhou 2022-09-17 22:37:49 +0800
  • 113179990d Merge branch 'develop' into audio_dev_merge #2400 Hui Zhang 2022-09-16 15:21:04 +0000
  • 592aa28551 Merge branch 'develop' into audio #2398 Hui Zhang 2022-09-16 14:57:04 +0000
  • 41f08ef9fc
    Merge pull request #2397 from PaddlePaddle/revert-2395-split_paddle_audio #2054 Hui Zhang 2022-09-16 22:44:24 +0800
  • 783b986038
    Revert "[audio]merge develop" #2397 YangZhou 2022-09-16 22:38:56 +0800
  • 5ee96b6376 update audio api in paddlespeech apps #2396 Yang Zhou 2022-09-16 21:09:14 +0800
  • 4f8fe16511
    Merge pull request #2395 from SmileGoat/split_paddle_audio YangZhou 2022-09-16 21:09:06 +0800
  • e6cbcca3e2
    fix ERNIE-SAT README, test=doc (#2392) TianYuan 2022-09-16 16:23:47 +0800
  • eac362057c
    add typehint for g2pw (#2390) TianYuan 2022-09-16 16:00:52 +0800
  • 2ce64f5de9 fix ERNIE-SAT README, test=doc #2392 TianYuan 2022-09-16 06:44:12 +0000
  • 68c2ec7563
    Merge pull request #2391 from Zth9730/update_result Zth9730 2022-09-16 11:52:35 +0800
  • 838771ae47 merge develop #2395 Yang Zhou 2022-09-16 11:32:45 +0800
  • 12a3d6b7df
    Merge pull request #2388 from SmileGoat/split_paddle_audio Hui Zhang 2022-09-16 10:38:30 +0800
  • 4ac206e22f update wenetspeech RESULT.md, test=doc #2391 tianhao zhang 2022-09-16 02:38:17 +0000
  • 7261d86344 add test & benchmark #2388 Yang Zhou 2022-09-15 21:12:57 +0800
  • 6d804ef64a add typehint for g2pw #2390 TianYuan 2022-09-15 12:50:35 +0000
  • 2244b531d5
    Merge branch 'PaddlePaddle:develop' into develop liangym 2022-09-15 20:08:17 +0800
  • b8c55c48a5 Merge branch 'develop' of github.com:iftaken/PaddleSpeech into dev-web #2389 iftaken 2022-09-15 15:57:05 +0800
  • 63700756ec update vc and tts mix iftaken 2022-09-15 15:55:58 +0800
  • cdf095595f
    [tts] finetune add frozen (#2385) liangym 2022-09-15 15:47:59 +0800
  • 4df081b954 split paddleaudio Yang Zhou 2022-09-15 15:17:26 +0800
  • 5821bbbb44
    Update train_infer_python.txt Zhao Yuting 2022-09-15 14:36:17 +0800
  • e5f0c8b2d2
    Update train_infer_python.txt Zhao Yuting 2022-09-15 14:25:23 +0800
  • c81d95a837
    Update benchmark_train.sh Zhao Yuting 2022-09-15 14:22:06 +0800
  • 2a3bc9f65b
    Update train_infer_python.txt Zhao Yuting 2022-09-15 14:20:31 +0800
  • 92b00cf61e
    Update train.py Zhao Yuting 2022-09-15 11:46:09 +0800
  • 92470f8456 finetune add frozen, test=tts #2385 lym0302 2022-09-15 03:05:43 +0000
  • b5f376e63b add voice clone function iftaken 2022-09-15 10:19:06 +0800
  • 0d7d87120b simplify feature pipeline graph Hui Zhang 2022-09-14 16:44:12 +0000
  • 2a95eaa8c6 Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into finetune #2381 lym0302 2022-09-14 08:17:54 +0000
  • adcf6e03e9
    Merge pull request #2382 from SmileGoat/ps_audio_dev YangZhou 2022-09-14 17:03:58 +0800
  • bc3ded383a fix typo #2382 YangZhou 2022-09-14 17:01:54 +0800
  • ccce14fbba
    Merge branch 'PaddlePaddle:develop' into develop liangym 2022-09-14 16:13:40 +0800
  • 324b166c52
    Removed useless spk_id in speech_server and streaming_tts_server from demos, and support bilingual server engine, test=tts (#2380) WongLaw 2022-09-14 16:11:12 +0800
  • ce2a5b1136 add frozen, test=tts lym0302 2022-09-14 07:01:16 +0000
  • 02679906e6
    Update tts_papers.md TianYuan 2022-09-14 15:22:25 +0800
  • 913fe44556 Removed useless spk_id in speech_server and streaming_tts_server from demos, and support bilingual server engine second, test=tts #2380 WongLaw 2022-09-14 07:16:05 +0000
  • dcb42cb66c Removed useless spk_id in speech_server and streaming_tts_server from demos, and support bilingual server engine. WongLaw 2022-09-14 06:59:41 +0000
  • fab5b3a3a6
    Merge branch 'PaddlePaddle:develop' into develop WongLaw 2022-09-14 14:35:38 +0800
  • 80b180217d
    [TTS] fix some bugs of ERNIE-SAT (#2378) TianYuan 2022-09-14 10:37:03 +0800
  • d7bf6c0054 fix for comments, test=tts #2378 TianYuan 2022-09-13 12:32:47 +0000
  • 578e57d2fa fix ernie_sat, test=tts TianYuan 2022-09-13 12:04:48 +0000
  • 8690a00bd8 add feature pipeline layer(cmvn, fbank), but to_static and jit.layer output is not equal Hui Zhang 2022-09-13 09:54:48 +0000
  • ec571bb0d1
    Update README.md TianYuan 2022-09-13 16:56:03 +0800
  • 67709155e9 add chunk conformer config from release model Hui Zhang 2022-09-13 08:29:21 +0000
  • 445cb2b08c
    fix prepare.sh (#2376) yuehuayingxueluo 2022-09-13 15:05:33 +0800
  • 07f566e0a5
    Merge pull request #2372 from Zth9730/fix_dp_init Hui Zhang 2022-09-13 14:10:58 +0800
  • 02ac117dfb
    Merge pull request #2373 from Zth9730/update_result Hui Zhang 2022-09-13 14:10:45 +0800
  • f37162f841 fix prepare.sh #2376 yuehuayingxueluo 2022-09-13 02:59:59 +0000
  • f7620c0de9
    Merge branch 'wav2vec' into wav2vec2 #2374 Zth9730 2022-09-10 13:04:32 +0800
  • c51da12b7f wav2vec2 pipeline tianhao zhang 2022-09-09 16:10:25 +0000
  • 3a8869fba4 rm to_static decarator; configure jit save for ctc_activation Hui Zhang 2022-09-09 15:50:11 +0000
  • 1c9f238ba0 configurable export Hui Zhang 2022-09-09 15:45:26 +0000
  • 08c3ceb04b update wenetspeech streaming coformer result #2373 tianhao zhang 2022-09-09 15:40:37 +0000
  • 63aeb747b0 more comment Hui Zhang 2022-09-09 15:29:55 +0000
  • a7c6c54e75 fix Hui Zhang 2022-09-09 15:20:28 +0000
  • d638325c46 do not jit save forward; using slice for zeros([0,0,0,0]) tensor Hui Zhang 2022-09-09 15:09:29 +0000
  • b9bc4a89a4 Merge branch 'hongliang0909' of https://github.com/david-95/PaddleSpeech into hongliang0909 david.95 2022-09-09 18:26:16 +0800
  • 663e3ab58e fix dp init #2372 tianhao zhang 2022-09-09 09:52:49 +0000
  • fdcc8c0427
    Update README.md TianYuan 2022-09-09 17:49:20 +0800
  • 08b9c45811 fix dp init tianhao zhang 2022-09-09 09:26:41 +0000
  • 6745e9dd6b fix dp init tianhao zhang 2022-09-09 09:23:56 +0000
  • 598eb1a5ef Merge branch 'develop' into fix_dp_init tianhao zhang 2022-09-09 08:58:37 +0000
  • 989b755e8e
    Revised must_neural_tone_words, test=doc. (#2370) WongLaw 2022-09-09 16:55:58 +0800
  • 9560d650db fix dp init tianhao zhang 2022-09-09 08:30:10 +0000
  • 26e3bbceaa
    update __init__.py, test=tts #2370 TianYuan 2022-09-09 16:12:14 +0800
  • 0975a332c4
    Update README.md TianYuan 2022-09-09 15:53:14 +0800
  • a1f87f9b40 Revised must_neural_tone_words. WongLaw 2022-09-09 07:53:00 +0000
  • cb7b2cab10
    Merge branch 'PaddlePaddle:develop' into develop WongLaw 2022-09-09 15:37:59 +0800
  • 8e2aee7b5e fix tone bug about 3 chinese chars have two tone5, test=tts #2369 david.95 2022-09-09 14:12:46 +0800
  • 232ab1958a Merge branch 'hongliang0909' of https://github.com/david-95/PaddleSpeech into hongliang0909-2 david.95 2022-09-09 14:03:23 +0800
  • 7edc39d03c add fix for 3 chinese chars, and 2nd char tone should not be 5, test=tts david.95 2022-09-09 12:14:43 +0800
  • b9758adb21 add fix for 3 chinese chars, and 2nd char tone should not be 5, test=tts david.95 2022-09-09 12:13:26 +0800
  • 82c97138fc
    Merge pull request #2367 from david-95/hongliang0909 TianYuan 2022-09-09 12:09:51 +0800
  • 61422e71e3 add tool to compare test badcase and add run examples,test=tts #2367 david.95 2022-09-09 11:34:03 +0800
  • 7e4f3b029c
    Merge pull request #2359 from yt605155624/add_vc2 TianYuan 2022-09-09 11:02:07 +0800
  • 881618dc2a add tool to compare two tests results, show difference -t tts david.95 2022-09-09 10:54:29 +0800
  • b1f51c3893
    Merge branch 'PaddlePaddle:develop' into develop WongLaw 2022-09-08 20:39:08 +0800
  • e04f111b8a
    Added pre-install doc for G2P and TN modules and updated the dependency version of pypinyin (#2364) WongLaw 2022-09-08 20:34:14 +0800
  • 82e04d7815 fix trianer tianhao zhang 2022-09-08 12:28:19 +0000
  • e1c6acb987 Added pre-install doc for G2P and TN modules and updated the dependency version of pypinyin second, test=doc #2364 WongLaw 2022-09-08 12:26:04 +0000
  • 5efb5db633 Added pre-install doc for G2P and TN modules and updated the dependency version of pypinyin, test=doc WongLaw 2022-09-08 12:13:20 +0000
  • b76bcc482e
    Delete CHANGELOG.md TianYuan 2022-09-08 19:33:52 +0800
  • f7873773bf
    uadd __init__.py for VITS, test=tts (#2362) TianYuan 2022-09-08 19:10:38 +0800
  • 17aef13d69 uadd __init__.py for VITS, test=tts #2362 TianYuan 2022-09-08 10:15:03 +0000
  • 056622d5f6 update speech_server config, test=tts #2359 TianYuan 2022-09-08 07:53:48 +0000
  • 5ae5e6819c update readme, test=tts TianYuan 2022-09-08 06:45:48 +0000
  • 35c6ffa90b Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into add_vc2 TianYuan 2022-09-08 02:47:15 +0000
  • e622f42d92 add aishell3 voice cloning with ECAPA-TDNN spk encoder TianYuan 2022-09-07 11:20:41 +0000