All pull requests

Pull requests

• docs: clarify channelwise behavior of CumulativeLayerNorm

  #3105·j45856021-dev opened Oct 14, 2026·6 tasks done·

  ·
  1

• chore: remove the usage of old weight_norm

  #3104·Decodetalkers opened Oct 13, 2026Contributor·8 of 13 tasks·

  ·

• Fix wer_summary reporting WER=0.0 when all scored references are empty

  #3102·Virtuoso461 opened Oct 12, 2026·

  ·

• Exclude padding when relative loss lengths round above an integer

  #3098·antonsoo opened Oct 9, 2026·7 of 13 tasks·

  ·

• Preserve batches when a distributed worker gets only one

  #3097·antonsoo opened Oct 9, 2026·7 of 13 tasks·

  ·

• Add formant estimation to vocal features

  #3096·pplantinga opened Oct 6, 2026Collaborator·

  ·

• Fix optimizer selection in SENSE recipe

  #3094·MaryemBouziane opened Oct 6, 2026Contributor·

  ·

• Use reference length as the denominator of WeightedErrorRateStats

  #3089·MohammadHijjawi97 opened Sep 28, 2026·7 of 13 tasks·

  ·

• fix(transformer): enforce max_len in make_transformer_src_tgt_masks

  #3086·FinalSunFlower opened Sep 14, 2026·

  ·
  1

  2

• Fix DNS composite_eval.py always raising TypeError (eval_composite missing sample_rate)

  #3079·Anai-Guo opened Aug 31, 2026·

  ·

• Fix BinaryMetricStats DER denominator

  #3078·Kayvan-Zahiri opened Aug 30, 2026Contributor·7 tasks done·

  ·

• fix(inference): make DiffWaveVocoder.forward and PIQAudioInterpreter.forward callable

  #3077·Anai-Guo opened Aug 29, 2026·6 of 7 tasks·

  ·

• Make RelPosEncXL able to encode the sign of the relative position

  #3073·yentur opened Aug 9, 2026·7 tasks done·

  ·

• [Code from Samsung AI Cambridge] BESTOW streaming for speech-to-text translation

  #3059·TParcollet opened Jun 3, 2026Collaborator·

  ·

• Bump gitpython from 3.1.37 to 3.1.47 in /recipes/BinauralWSJ0Mix

  dependenciespython
  #3051·dependabot[bot] opened Apr 26, 2026Bot·

  ·

• Add ECAPA2 to VoxCeleb

  #3039·othman-istaiteh opened Mar 4, 2026·7 of 13 tasks·

  ·
  19

• Optimize minDCF memory footprint

  #3037·othman-istaiteh opened Feb 27, 2026·6 of 13 tasks·

  ·

• fix spectrogram drop mask staring position

  #3036·gfdb opened Feb 17, 2026Contributor·13 tasks·

  ·
  3

• add mossformer2 training with Aishell1 mix

  #3035·huangzj421 opened Feb 13, 2026Contributor·13 tasks·

  ·
  2

• Bump virtualenv from 20.31.2 to 20.36.1

  dependenciespython:uv
  #3024·dependabot[bot] opened Feb 3, 2026Bot·

  ·

• Add Myst children speech recipe

  recipes
  #2997·Usanter opened Nov 17, 2025·7 tasks done·

  ·
  26

• Add type checking with PyRight to CI (from Samsung AI Center Cambridge)

  #2901·rogiervd opened May 13, 2025Contributor·4 of 13 tasks·

  ·
  7

• Whisper updates

  #2878·Adel-Moumen opened Apr 8, 2025Collaborator·13 tasks·

  ·

• Tokotron: Tokenized TTS (lite version - minimal dependencies)

  recipes
  #2849·flexthink opened Mar 4, 2025Collaborator·5 of 13 tasks·

  ·

  · v1.2.0
  13

  

• Added LMAC-TD [ICASSP'25]

  #2838·fpaissan opened Feb 27, 2025Collaborator·13 tasks·

  ·

  · v1.1.0
  1