Commit Graph

  • d1410c52e7 CI for streaming zipformer CTC + HLG decoding Fangjun Kuang 2024-03-18 19:44:17 +08:00
  • 557bf292a2 Update docker Fangjun Kuang 2024-03-18 19:12:44 +08:00
  • 4917ac8bab
    allow export of onnx-streaming-models with other than 80dim input features (#1556) Karel Vesely 2024-03-18 11:43:29 +01:00
  • 40668e4e8b Add streaming HLG decoding for zipformer CTC. Fangjun Kuang 2024-03-18 18:21:35 +08:00
  • 2bb3a4bc7c allow export of onnx-streaming-models with other than 80dim input features Karel Vesely 2024-03-18 11:03:00 +01:00
  • eec12f053d
    Use piper_phonemize as text tokenizer in vctk TTS recipe (#1522) zr_jin 2024-03-18 17:53:52 +08:00
  • 9b0eae3b4a
    fixes for init value of diagnostics.TensorDiagnosticOptions (#1555) zr_jin 2024-03-18 17:14:29 +08:00
  • 4a8bd4294a removed unnecessary warning jinzr 2024-03-18 16:50:49 +08:00
  • bf2f94346c
    Enabling char_level and compute_CER for aishell recipe (#1554) zr_jin 2024-03-18 11:57:47 +08:00
  • 3b4e86ed42 init commit jinzr 2024-03-18 11:21:48 +08:00
  • f9577510ab
    Update egs/aishell/ASR/conformer_mmi/decode.py zr_jin 2024-03-18 11:20:13 +08:00
  • 23bd455388 init fix jinzr 2024-03-18 11:15:44 +08:00
  • fa73dc54a5 misc. update jinzr 2024-03-18 10:39:01 +08:00
  • d4fda2b354 copy files for aishell3 Fangjun Kuang 2024-03-18 10:07:50 +08:00
  • 8b867affee first working version Fangjun Kuang 2024-03-18 10:04:07 +08:00
  • 7ea100a26a
    Merge branch 'k2-fsa:master' into dev/tts/vctk/tokenizer zr_jin 2024-03-18 09:29:13 +08:00
  • 6993183dd7 Update preprocess_commonvoice.py jinzr 2024-03-15 19:31:35 +08:00
  • 2dfd5dbf8b
    Add LoRA for Zipformer (#1540) Xiaoyu Yang 2024-03-15 17:19:23 +08:00
  • d9a0ab59db fixed formatting issue jinzr 2024-03-15 11:31:21 +08:00
  • e62e16e6d5 updated with scripts for streaming decode jinzr 2024-03-15 11:15:07 +08:00
  • 77bfecd3d8 fix style marcoyang 2024-03-15 11:05:45 +08:00
  • 3560e2260e Merge branch 'master' into dev/cv-zipformer jinzr 2024-03-15 11:03:32 +08:00
  • bea63ca619 Update asr_datamodule.py jinzr 2024-03-15 11:00:03 +08:00
  • 678ad2b8a9 Update preprocess_commonvoice.py jinzr 2024-03-15 10:49:12 +08:00
  • 06bca2ffed misc. update jinzr 2024-03-15 10:43:33 +08:00
  • 030365f168 misc. update jinzr 2024-03-15 10:07:15 +08:00
  • d77b03517f misc. fix jinzr 2024-03-15 09:49:28 +08:00
  • 7d01eb46db misc fix jinzr 2024-03-15 09:43:26 +08:00
  • 7ead73f746 update readme marcoyang 2024-03-14 18:23:16 +08:00
  • 390f01653f resolve conflict marcoyang 2024-03-14 18:22:36 +08:00
  • cf92d40a9d update README marcoyang 2024-03-14 18:19:06 +08:00
  • c7180b9869 add missing file marcoyang 2024-03-14 17:19:09 +08:00
  • af04e7d7be support export and merge weight of a LoRA zipformer marcoyang 2024-03-14 17:18:51 +08:00
  • d5309db7f7
    Update decode.py fenghaojin 2024-03-14 17:00:16 +08:00
  • 4481dccc00 deploy: f28c05f4f51b271aa68811fb12358a301ff4ba0c marcoyang1998 2024-03-14 04:29:08 +00:00
  • c0924f0a2f register the weight and bias marcoyang 2024-03-14 12:20:45 +08:00
  • f28c05f4f5
    Documentation for adapter fine-tuning (#1545) Xiaoyu Yang 2024-03-14 12:18:49 +08:00
  • 5723ce85c8 Copy files Fangjun Kuang 2024-03-14 12:06:47 +08:00
  • eb132da00d
    additional instruction for the grad_scale is too small error (#1550) zr_jin 2024-03-14 11:33:49 +08:00
  • 72b97959d4 init commit jinzr 2024-03-14 10:56:07 +08:00
  • e9f86df7d5 Update asr_datamodule.py jinzr 2024-03-14 09:47:04 +08:00
  • 53fb384488 scripts updated jinzr 2024-03-14 09:45:25 +08:00
  • ed3d25b768 added scripts for processing validated data jinzr 2024-03-13 20:21:04 +08:00
  • ea0b6311f1
    Merge branch 'k2-fsa:master' into k2ssl Yifan Yang 2024-03-13 19:52:14 +08:00
  • c1b715f7df deploy: 15bd9a841e347a8881fc6df599fd440ebb118da4 csukuangfj 2024-03-13 10:22:59 +00:00
  • 15bd9a841e
    add CI for ljspeech (#1548) Fangjun Kuang 2024-03-13 17:39:01 +08:00
  • e979bf5e93 Update train_char.py jinzr 2024-03-13 17:22:32 +08:00
  • 952eb41ff7 add CI for ljspeech Fangjun Kuang 2024-03-13 11:15:44 +08:00
  • 58041c1fb6 Update train_char.py jinzr 2024-03-13 14:33:59 +08:00
  • c1eb2adf64 Update train_char.py jinzr 2024-03-13 12:46:30 +08:00
  • 921d34abcb Update train_char.py jinzr 2024-03-13 12:17:51 +08:00
  • 303eb99e47 Update train_char.py jinzr 2024-03-13 12:12:55 +08:00
  • 569920266c Update train_char.py jinzr 2024-03-13 12:04:39 +08:00
  • 9bf88ac3b1 Update train_char.py jinzr 2024-03-13 12:01:34 +08:00
  • 4413713a05 added char based training scripts jinzr 2024-03-13 11:58:47 +08:00
  • 7d34116f5f minor fixes jinzr 2024-03-13 11:17:19 +08:00
  • eaceb691d8 Update preprocess_commonvoice.py jinzr 2024-03-13 11:09:22 +08:00
  • 05b3381bce deploy: d406b41cbda16df57f4cbe0ee091032a1df7fce3 csukuangfj 2024-03-13 03:02:00 +00:00
  • d406b41cbd
    Doc: Add page for installing piper-phonemize (#1547) Fangjun Kuang 2024-03-13 11:01:18 +08:00
  • 743dbf3916 Doc: Add page for installing piper-phonemize Fangjun Kuang 2024-03-13 10:57:53 +08:00
  • b30a4d6162 updated scripts for text norm jinzr 2024-03-13 10:57:59 +08:00
  • 09a358a23e Update preprocess_commonvoice.py jinzr 2024-03-13 10:36:50 +08:00
  • a39aa8a59d scripts updated jinzr 2024-03-13 10:16:35 +08:00
  • c3f6f28116
    Zipformer recipe for Cantonese dataset MDCC (#1537) zr_jin 2024-03-13 10:01:28 +08:00
  • 17b23ae3bd doc str fixed jinzr 2024-03-13 09:46:00 +08:00
  • 9321f8ab7a add librilight yifanyeung 2024-03-13 00:14:20 +08:00
  • 5dd57a5d35 deploy: 81f518ea7c4dc1e709bb10f21aac55dd33712649 csukuangfj 2024-03-12 15:27:36 +00:00
  • 81f518ea7c
    Support different tts model types. (#1541) Fangjun Kuang 2024-03-12 22:29:21 +08:00
  • 4c41443e13 minor fixes Fangjun Kuang 2024-03-12 22:28:01 +08:00
  • 4abfdc7f57 Update doc Fangjun Kuang 2024-03-12 22:25:23 +08:00
  • a92c6df76a minor fixes Fangjun Kuang 2024-03-12 21:59:47 +08:00
  • 7f9cbf1ce2 typo fixes Fangjun Kuang 2024-03-12 21:53:31 +08:00
  • 71e77e0f7c Upate reamd to add a link to a medium model Fangjun Kuang 2024-03-12 16:45:50 +08:00
  • 9681263c0d Update README Fangjun Kuang 2024-03-12 16:39:14 +08:00
  • 750e2ac035 Update prepare.sh jinzr 2024-03-12 14:35:15 +08:00
  • 204a3b2fb2 arg type fixed jinzr 2024-03-12 12:44:26 +08:00
  • 959906e9dc
    Correct alimeeting download link (#1544) BannerWang 2024-03-12 12:44:09 +08:00
  • d887bf8c63 updated scripts for text jinzr 2024-03-12 12:40:44 +08:00
  • d45e4c61e1 Update prepare.sh jinzr 2024-03-12 12:36:52 +08:00
  • a9df06cef4 Update prepare.sh jinzr 2024-03-12 12:34:27 +08:00
  • 9820bf92f6 updated jinzr 2024-03-12 12:24:24 +08:00
  • 4cae6b6c9a text_norm updated jinzr 2024-03-12 12:19:14 +08:00
  • d35cedcd85 text_norm updated jinzr 2024-03-12 12:18:22 +08:00
  • 4a1d4be94a added scripts for char-based lang prep jinzr 2024-03-12 12:12:35 +08:00
  • 6f56309dce add docs for adapter fine-tuning marcoyang 2024-03-12 11:52:56 +08:00
  • 52da82def2 Correct alimeeting download link BannerWang 2024-03-12 11:10:26 +08:00
  • e69b60e579 enable the grad_scale is too small error jinzr 2024-03-11 23:14:14 +08:00
  • 687b9f1c45 fixed formatting issues jinzr 2024-03-11 23:11:04 +08:00
  • ddefabcb7a added scripts jinzr 2024-03-11 23:09:19 +08:00
  • e472fa6840
    fix CutMix init parameter (#1543) jimmy1984xu 2024-03-11 18:37:26 +08:00
  • f0fef41a20 fix CutMix init parameter jimmyxu 2024-03-11 18:34:16 +08:00
  • 3009ba2d5e initial commit marcoyang 2024-03-11 15:17:29 +08:00
  • b33d3820db Support different tts model types. Fangjun Kuang 2024-03-11 12:42:43 +08:00
  • 6806810666 bug fix marcoyang 2024-03-11 12:18:03 +08:00
  • 3492d9415c add lora version of ActivationDropouAndLinear; currently a simple version marcoyang 2024-03-11 12:02:35 +08:00
  • a421792863 added scripts for streaming related stuff jinzr 2024-03-11 11:08:15 +08:00
  • b2d1975f0e init commit jinzr 2024-03-11 11:04:33 +08:00
  • 60691efddf added RESULTS.md jinzr 2024-03-11 10:59:32 +08:00
  • bb8f6b0ef7 add lora to the in_proj of the feedforward module marcoyang 2024-03-11 10:45:36 +08:00
  • 78b39d9a7d added scripts for exporting model jinzr 2024-03-11 09:38:42 +08:00