v.202308

espnet/espnet

版本发布时间: 2023-08-03 21:36:23

espnet/espnet最新发布版本:v.202409(2024-10-01 14:28:01)

What's Changed

Update tutorial by @ftshijt in https://github.com/espnet/espnet/pull/4648
Update tutorials by @ftshijt in https://github.com/espnet/espnet/pull/4898
add e-branchformer result for tedlium3 and add checker for text output length by @Some-random in https://github.com/espnet/espnet/pull/5130
Limit the Numpy version (<1.24) to fix CI error temporarily. by @simpleoier in https://github.com/espnet/espnet/pull/5162
[SVS] Add new recipes by @A-Quarter-Mile in https://github.com/espnet/espnet/pull/5158
Update README.md of CHiME-7 DASR: fixing typos by @popcornell in https://github.com/espnet/espnet/pull/5166
Fix typo in CONTRIBUTING.md by @eltociear in https://github.com/espnet/espnet/pull/5167
CHiME-7 DASR: Update install_dependencies.sh, fix lhotse version by @popcornell in https://github.com/espnet/espnet/pull/5168
Update TD-SpeakerBeam by @Emrys365 in https://github.com/espnet/espnet/pull/5155
Add pre-trained causal speech separation model and streaming demo by @LiChenda in https://github.com/espnet/espnet/pull/5172
KSC recipe by @khassanoff in https://github.com/espnet/espnet/pull/5171
[SVS] Add new recipe by @A-Quarter-Mile in https://github.com/espnet/espnet/pull/5173
Update AphasiaBank Recipe by @tjysdsg in https://github.com/espnet/espnet/pull/5104
fix the gradient backward issue when joint training with s3prl frontend by @simpleoier in https://github.com/espnet/espnet/pull/5159
Add installer for ParallelWaveGAN by @ftshijt in https://github.com/espnet/espnet/pull/4052
[GAN SVS] Add VISinger2, UHifiGAN, Avocodo by @jerryuhoo in https://github.com/espnet/espnet/pull/5123
[SVS] Update docs README.md by @South-Twilight in https://github.com/espnet/espnet/pull/5178
Update SVS README.md by @jerryuhoo in https://github.com/espnet/espnet/pull/5180
Adding eendss models by @soumimaiti in https://github.com/espnet/espnet/pull/5157
2022fall new task tutorial by @ftshijt in https://github.com/espnet/espnet/pull/5186
[SVS] Updates for recipes by @A-Quarter-Mile in https://github.com/espnet/espnet/pull/5187
[GAN SVS] fix phoneme predictor by @jerryuhoo in https://github.com/espnet/espnet/pull/5188
Update generate_librimix_sd.sh by @leepeiying in https://github.com/espnet/espnet/pull/5182
Bug fix for #5195 by @YosukeHiguchi in https://github.com/espnet/espnet/pull/5196
[SVS] Update on recipes by @A-Quarter-Mile in https://github.com/espnet/espnet/pull/5197
Update preprocessor.py by @sw005320 in https://github.com/espnet/espnet/pull/5200
Minor fixes for ML-SUPERB by @ftshijt in https://github.com/espnet/espnet/pull/5202
Quick fix for whisper specaug by @siddhu001 in https://github.com/espnet/espnet/pull/5206
espnet-spk data preparation part by @Jungjee in https://github.com/espnet/espnet/pull/5184
Fix M4singer multi-spk recipe by @ftshijt in https://github.com/espnet/espnet/pull/5201
Update Dataset link for mlsuperb by @ftshijt in https://github.com/espnet/espnet/pull/5216
Fix bug when score_type is set to normal in ml_superb by @ftshijt in https://github.com/espnet/espnet/pull/5217
Add new functions and fix some bugs in SE by @Emrys365 in https://github.com/espnet/espnet/pull/5193
Update import order by @ftshijt in https://github.com/espnet/espnet/pull/5229
Closed CHiME-7 DASR adding evaluation inference + adding support to use diarization baseline "pre-computed" JSONs (new PR) by @popcornell in https://github.com/espnet/espnet/pull/5228
Standalone Transducer v1.1 by @b-flo in https://github.com/espnet/espnet/pull/5140
Small fixes for Transducer by @b-flo in https://github.com/espnet/espnet/pull/5247
add asr2 task and librispeech recipe as an example. by @simpleoier in https://github.com/espnet/espnet/pull/5181
fix norm compatibility in scale discriminator by @kan-bayashi in https://github.com/espnet/espnet/pull/5240
CFSD, SECS metrics for TTS by @imdanboy in https://github.com/espnet/espnet/pull/5235
Add new SE recipes: chime1/enh1, chime2/enh1, reverb/enh1, and wsj0_2mix/tse1 by @Emrys365 in https://github.com/espnet/espnet/pull/5246
Fix bugs in mfa_format.py by @G-Thor in https://github.com/espnet/espnet/pull/5223
New features for SVS by @ftshijt in https://github.com/espnet/espnet/pull/5245
re-fix norm compatibility in scale discriminator by @kan-bayashi in https://github.com/espnet/espnet/pull/5249
add conv1d subsampling 3 and egs2/librispeech/asr2 wavlm_large_21 kmeans (1000/2000) results by @simpleoier in https://github.com/espnet/espnet/pull/5252
Revise the ESPnet-SE++ Joss paper to incorporate the feedback from the reviewer. by @neillu23 in https://github.com/espnet/espnet/pull/5212
Fix a bug in score script for ML-SUPERB by @ftshijt in https://github.com/espnet/espnet/pull/5254
Refactor prep_segments in SVS by @jerryuhoo in https://github.com/espnet/espnet/pull/5210
A minor fix for num_splits_ssl for training by @ftshijt in https://github.com/espnet/espnet/pull/5262
[SVS] add singing tacotron by @A-Quarter-Mile in https://github.com/espnet/espnet/pull/5233
Add script to use speaker averaged xvectors in TTS training by @G-Thor in https://github.com/espnet/espnet/pull/5244
Fix filling of waveform_buffer with samples for streaming inference by @espnetUser in https://github.com/espnet/espnet/pull/5267
Some name update for ml-superb by @ftshijt in https://github.com/espnet/espnet/pull/5276
Add support for K2 pruned transducer loss by @b-flo in https://github.com/espnet/espnet/pull/5268
Fix Transducer doc by @b-flo in https://github.com/espnet/espnet/pull/5306
Update installation.md by @kamo-naoyuki in https://github.com/espnet/espnet/pull/5291
Update install_nkf.sh by @sw005320 in https://github.com/espnet/espnet/pull/5300
Fix Cython version to pass the installation of libraries with Cython by @kan-bayashi in https://github.com/espnet/espnet/pull/5310
Update README.md by @sw005320 in https://github.com/espnet/espnet/pull/5315
Update setup.py by @sw005320 in https://github.com/espnet/espnet/pull/5316
Migrate recipe for nit_song070 from Muskit by @wwwbxy123 in https://github.com/espnet/espnet/pull/5251
[pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/espnet/espnet/pull/5294
A few updates for asr2 and hubert by @simpleoier in https://github.com/espnet/espnet/pull/5285
Add decode_options and hyp_cleaner in evaluate_whisper_inference by @pyf98 in https://github.com/espnet/espnet/pull/5272
update pyworld version by @kan-bayashi in https://github.com/espnet/espnet/pull/5319
fix a data preparation issue for librimix recipe. by @LiChenda in https://github.com/espnet/espnet/pull/5322
Update README.md in egs2/librimix/tse1 and egs2/wsj0_2mix/tse1 by @Emrys365 in https://github.com/espnet/espnet/pull/5289
fix the s3prl frontend gradient backprop bug, ensuring feature_grad_mult=1.0 by @simpleoier in https://github.com/espnet/espnet/pull/5297
ESPNet-SPK part 2 - training by @Jungjee in https://github.com/espnet/espnet/pull/5258
remove some tests in espnet1 integration test by @sw005320 in https://github.com/espnet/espnet/pull/5328
Fix random segments by @iamanigeeit in https://github.com/espnet/espnet/pull/5274
Skip CI for draft PR by @ftshijt in https://github.com/espnet/espnet/pull/5333
Update cancel.yml by @kan-bayashi in https://github.com/espnet/espnet/pull/5334
Update several SE recipes and bash scripts by @Emrys365 in https://github.com/espnet/espnet/pull/5327
Add PULL_REQUEST_TEMPLATE.md by @kan-bayashi in https://github.com/espnet/espnet/pull/5340
ESPnet-Spk part 3 - inference every epoch using EER by @Jungjee in https://github.com/espnet/espnet/pull/5314
Minimize espnet2 integration test by @kan-bayashi in https://github.com/espnet/espnet/pull/5324
PR Labels for CI control by @Fhrozen in https://github.com/espnet/espnet/pull/5320
Split ci into several jobs by @kan-bayashi in https://github.com/espnet/espnet/pull/5343
Update CONTRIBUTING.md by @sw005320 in https://github.com/espnet/espnet/pull/5335
Update Scoring for Speech Summarization from NLG-Eval to Huggingface Evaluate by @roshansh-cmu in https://github.com/espnet/espnet/pull/5341
Fix documentation skip CI by @Fhrozen in https://github.com/espnet/espnet/pull/5351
Update the usage by @sw005320 in https://github.com/espnet/espnet/pull/5349
Docker Update by @Fhrozen in https://github.com/espnet/espnet/pull/5321
Update installation.md by @sw005320 in https://github.com/espnet/espnet/pull/5348
Fix doc condition by @kan-bayashi in https://github.com/espnet/espnet/pull/5355
Update issue templates by @sw005320 in https://github.com/espnet/espnet/pull/5357
Update Contribution.md by @Fhrozen in https://github.com/espnet/espnet/pull/5352
Fix .mergify condition by @kan-bayashi in https://github.com/espnet/espnet/pull/5354
Reduce ffmpeg installation time in ci by @kan-bayashi in https://github.com/espnet/espnet/pull/5356
Update CI table by @kan-bayashi in https://github.com/espnet/espnet/pull/5359
Clean workflow files by @kan-bayashi in https://github.com/espnet/espnet/pull/5360
Couple of tweaks for asr2.sh for the HF hub upload by @akreal in https://github.com/espnet/espnet/pull/5362
Update TEMPLATE_HF_Readme.md (fix bash typo) by @akreal in https://github.com/espnet/espnet/pull/5361
Add discrete-token ASR for LibriSpeech 100h by @akreal in https://github.com/espnet/espnet/pull/5350
Whisper fine-tuning recipes for CHiME-4 and WSJ by @YoshikiMas in https://github.com/espnet/espnet/pull/5342
Fix bug in ngram training in slu.sh by @siddhu001 in https://github.com/espnet/espnet/pull/5364
Add musdb18 recipe for music source separation by @Emrys365 in https://github.com/espnet/espnet/pull/5338
Bugfix: JETS CTCLoss by @imdanboy in https://github.com/espnet/espnet/pull/5288
Check the value of n_shift == upsample_factor in GAN_TTS by @imdanboy in https://github.com/espnet/espnet/pull/5299
MFA format fix by @iamanigeeit in https://github.com/espnet/espnet/pull/5275
add --num-workers 0 option to enable coverage to truck data loader by @kan-bayashi in https://github.com/espnet/espnet/pull/5368
ESPnet-SPK: fix data augment by @Jungjee in https://github.com/espnet/espnet/pull/5347
A few minor fixes for SSL by @ftshijt in https://github.com/espnet/espnet/pull/5265
remove unused file + small typo/style by @b-flo in https://github.com/espnet/espnet/pull/5346
ESPnet-SPK: EER validation efficiency improvement by @Jungjee in https://github.com/espnet/espnet/pull/5358
New Architectures for ST by @brianyan918 in https://github.com/espnet/espnet/pull/4815
[SVS] Add CI test by @A-Quarter-Mile in https://github.com/espnet/espnet/pull/5269
Add causal LM to Hugging Face Transformers Decoder by @akreal in https://github.com/espnet/espnet/pull/5313
Make make_pad_mask onnx convertible by @Masao-Someki in https://github.com/espnet/espnet/pull/5326
fix numerical error of parallel wavegan compatibility test in CI by @kan-bayashi in https://github.com/espnet/espnet/pull/5380
Add LibriTTS-R recipe by @ShigekiKarita in https://github.com/espnet/espnet/pull/5379
minor fix: correct wrong comments by @imdanboy in https://github.com/espnet/espnet/pull/5378
Add quotation marks to install_datasets.sh by @qmeeus in https://github.com/espnet/espnet/pull/5387

New Contributors

@khassanoff made their first contribution in https://github.com/espnet/espnet/pull/5171
@leepeiying made their first contribution in https://github.com/espnet/espnet/pull/5182
@Jungjee made their first contribution in https://github.com/espnet/espnet/pull/5184
@wwwbxy123 made their first contribution in https://github.com/espnet/espnet/pull/5251

Full Changelog: https://github.com/espnet/espnet/compare/v.202304...v.202308

相关地址：原始地址下载(tar) 下载(zip)

查看：2023-08-03发行的版本