What's Changed

• Support arbitrary language finetune for Whisper models. by @pengchengguo in https://github.com/espnet/espnet/pull/5344
• Update Dipco Data URL by @Fhrozen in https://github.com/espnet/espnet/pull/5391
• Update readme in TEMPLATE/svs1 by @linyueqian in https://github.com/espnet/espnet/pull/5394
• add gramvaani asr recipe by @bloodraven66 in https://github.com/espnet/espnet/pull/5366
• ESPnet-SPK: sampler by @Jungjee in https://github.com/espnet/espnet/pull/5365
• Adding general data augmentation methods for speech preprocessing by @Emrys365 in https://github.com/espnet/espnet/pull/5370
• Update of several SE recipes and some minor fixes by @Emrys365 in https://github.com/espnet/espnet/pull/5401
• Reproducing MIMOIRIS by @YoshikiMas in https://github.com/espnet/espnet/pull/5409
• Kathbath asr by @bloodraven66 in https://github.com/espnet/espnet/pull/5369
• Add pytorch2.0.1 to CI by @kamo-naoyuki in https://github.com/espnet/espnet/pull/5413
• [skip ci] Update README.md by @kamo-naoyuki in https://github.com/espnet/espnet/pull/5417
• In spec_augment.py, check whether an array is writeable before modifying it inplace by @mdecerbo in https://github.com/espnet/espnet/pull/5416
• Docker updates for local builds by @Fhrozen in https://github.com/espnet/espnet/pull/5406
• fix typo in TEMPLATE/svs1/README.md by @linyueqian in https://github.com/espnet/espnet/pull/5426
• Update install_mwerSegmenter.sh by @sw005320 in https://github.com/espnet/espnet/pull/5437
• Support Whisper-style training as a new task S2T by @pyf98 in https://github.com/espnet/espnet/pull/5120
• fix twice numpy installation issue by @kan-bayashi in https://github.com/espnet/espnet/pull/5447
• Add Whisper SOT recipe for Librimix by @LiChenda in https://github.com/espnet/espnet/pull/5371
• Update for the JOSS paper editor review by @neillu23 in https://github.com/espnet/espnet/pull/5418
• Add the VOiCES recipe for ASR by @Emrys365 in https://github.com/espnet/espnet/pull/5448
• Improve diacritic compatibility in data_prep.pl preprocessing scripts by @zuazo in https://github.com/espnet/espnet/pull/5445
• [WIP] create recipe for acesinger by @linyueqian in https://github.com/espnet/espnet/pull/5431
• Add BibleTTS recipe by @wyh2000 in https://github.com/espnet/espnet/pull/5436
• ASR2 CHiME4 & Gigaspeech Recipes by @yichen14 in https://github.com/espnet/espnet/pull/5434
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/espnet/espnet/pull/5427
• Simple fix to reduce test_slu_inference time by @siddhu001 in https://github.com/espnet/espnet/pull/5460
• Do not use root logger in Beamsearch by @vsd-vector in https://github.com/espnet/espnet/pull/5454
• Fix whisper test by @siddhu001 in https://github.com/espnet/espnet/pull/5464
• Add doc for OWSM by @pyf98 in https://github.com/espnet/espnet/pull/5463
• Speech-to-speech translation Task by @ftshijt in https://github.com/espnet/espnet/pull/4859
• AVSR recipes on LRS3 using pre-trained AV-HuBERT model by @ms-dot-k in https://github.com/espnet/espnet/pull/5456
• Support LoRA based large model finetuning. by @pengchengguo in https://github.com/espnet/espnet/pull/5400
• Multilingual Librispeech (MLS) refactor ASR1 recipe by @juice500ml in https://github.com/espnet/espnet/pull/5323
• Add phonemized LibriTTS ASR recipe by @akreal in https://github.com/espnet/espnet/pull/5466
• Update the Enh framework to support training with variable numbers of speakers by @Emrys365 in https://github.com/espnet/espnet/pull/5414
• speed up TFGridNet code by @zqwang7 in https://github.com/espnet/espnet/pull/5395
• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/espnet/espnet/pull/5468
• ASR2 recipe on Tedlium3 dataset by @kohei0209 in https://github.com/espnet/espnet/pull/5331
• Create README.md in OWSM v1 by @pyf98 in https://github.com/espnet/espnet/pull/5489
• Update setup.py by @sw005320 in https://github.com/espnet/espnet/pull/5490
• Fix default value in ML-SUPERB by @ftshijt in https://github.com/espnet/espnet/pull/5492
• Fix bugs of Whisper SOT. by @pengchengguo in https://github.com/espnet/espnet/pull/5494
• Multilingual Librispeech ASR2 + ASR1 baselines by @juice500ml in https://github.com/espnet/espnet/pull/5441
• Add a new SE recipe combining five public corpora by @Emrys365 in https://github.com/espnet/espnet/pull/5484
• Update .mergify.yml by @kamo-naoyuki in https://github.com/espnet/espnet/pull/5502
• update version to 202310 by @kan-bayashi in https://github.com/espnet/espnet/pull/5501

New Contributors

• @linyueqian made their first contribution in https://github.com/espnet/espnet/pull/5394
• @mdecerbo made their first contribution in https://github.com/espnet/espnet/pull/5416
• @zuazo made their first contribution in https://github.com/espnet/espnet/pull/5445
• @wyh2000 made their first contribution in https://github.com/espnet/espnet/pull/5436
• @yichen14 made their first contribution in https://github.com/espnet/espnet/pull/5434
• @vsd-vector made their first contribution in https://github.com/espnet/espnet/pull/5454
• @ms-dot-k made their first contribution in https://github.com/espnet/espnet/pull/5456
• @juice500ml made their first contribution in https://github.com/espnet/espnet/pull/5323
• @kohei0209 made their first contribution in https://github.com/espnet/espnet/pull/5331

Full Changelog: https://github.com/espnet/espnet/compare/v.202308...v.202310