Pull Requests ggml-org/whisper.cpp

whisper : fix no_speech_prob and VAD token timestamps in JSON output

#4068 opened 2026-09-16 13:04 by gonuit

whisper.wasm : expose segments and token data to the JS layer

#4066 opened 2026-09-14 15:50 by ubmids

vad : reject n_encoder_layers other than 4 in model load

#4064 opened 2026-09-13 02:28 by apollo-2006

Copilot/fix docker image push action

#4061 opened 2026-09-12 06:39 by AKB0700

whisper : fail gracefully when model weight buffer allocation fails (#3386)

#4055 opened 2026-09-10 18:57 by ousamabenyounes

go : free CString allocations in lang_id and params setters

#4054 opened 2026-09-10 15:45 by 22elix3r

whisper : add language title API (#535)

#4049 opened 2026-09-09 13:50 by wangyusheng1985

ci : cover GGML_BACKEND_DL in ubuntu-22-clang-arm64

#4047 opened 2026-09-08 16:57 by apollo-2006

devops : reduce Vulkan Docker image to 39.4% of its original size (now 692 MB)

#4038 opened 2026-09-06 22:07 by turicas

cmake : add version.h.in files for whisper and parakeet

#4033 opened 2026-09-04 05:25 by danbev

release : publish macOS CLI binaries (arm64, x64, universal)

#4029 opened 2026-09-02 18:01 by apollo-2006

Cmake edited so that in tests : we can auto-download base.en model to pass the ctest without manually downloading the model

#4028 opened 2026-09-02 16:20 by GodRishUniverse

tests : update parakeet download instruction [no ci]

#4023 opened 2026-08-28 14:01 by danbev

harden: detected non-static command inside ` in extsources.rb...

#4021 opened 2026-08-27 12:20 by anupamme

docs : add note about ggml PRs in CONTRIBUTING.md [no ci]

#4020 opened 2026-08-27 11:12 by danbev

models : fix n_text_ctx taken from max_length instead of max_target_positions

#3987 opened 2026-08-12 14:38 by axiom-of-choice

cli : drop invalid UTF-8 bytes from JSON output

#3980 opened 2026-08-09 21:30 by ousamabenyounes

fix: Slow output stage after "saving output to ..." when using --dialize (-di)

#3976 opened 2026-08-07 08:49 by mitslabo

sycl : fix Q8_0/k-quant reorder get_rows (garbage output with GGML_SYCL_ENABLE_OPT)

#3964 opened 2026-08-02 20:28 by xuhancn

Fix no_speech_prob calculation

#3945 opened 2026-07-18 19:08 by mculbert

whisper : mask padded K/V in flash-attention encoder and cross-attention

#3941 opened 2026-07-16 09:55 by gooofy

ggml-cpu: gelu optimizqation using simd

#3939 opened 2026-07-09 21:23 by ameya-ms

Fix issue #3269: Account for duration and offset parameters

#3934 opened 2026-07-07 09:49 by mustardpower

Fixes issue: #3924

#3929 opened 2026-07-06 11:10 by michaelsam94

stream : add interactive start/stop mode (-i)

#3926 opened 2026-07-04 12:54 by ailakshya

whisper : reject audio too short for reflective padding

#3925 opened 2026-07-04 10:18 by hellopahe

examples: resolve whisper-cli models from the HuggingFace cache (-hf/-hff)

#3922 opened 2026-07-02 20:39 by djd0723

tests: cover audio buffer decoding

#3911 opened 2026-06-25 22:28 by jamesachurchill

addon.node : support cancelling transcription via AbortSignal

#3909 opened 2026-06-25 08:03 by buxuku

examples : add parakeet-server example

#3904 opened 2026-06-22 14:13 by danbev