Overview

• Add initial VAD support - feedback welcome and appreciated
• Metal FA improvements

M2 Ultra

Flash Attention ON:

Flash Attention OFF:

What's Changed

• docs : add xcframework section to README.md [no ci] by @danbev in #2997
• sync : ggml by @ggerganov in #2992
• whisper.wasm : fix unknown language issue by @danbev in #3000
• examples : update server.py to match github pages app [no ci] by @danbev in #3004
• rename : ggerganov -> ggml-org by @ggerganov in #3005
• whisper : fix "bench-all outputs an invalid result on larger models" by @fujimotos in #3002
• tests : add script to benchmark whisper.cpp on LibriSpeech corpus by @fujimotos in #2999
• ruby : Change homepage URI in Ruby gemspec by @KitaitiMakoto in #3007
• fix dead link to models in readme by @gregsadetsky in #3006
• Update uri.rb by @Olli in #3016
• Update ruby_whisper_params.c by @Olli in #3022
• xcf : use check for visionos build version by @danbev in #3021
• Fix README.md by @ekaitz-zarraga in #3024
• docs : document how to use 'WHISPER_FFMPEG' build option by @fujimotos in #3029
• whisper : reduce delta_min from 1000ms to 100ms by @ggerganov in #3028
• support max_context api for addon.node by @buxuku in #3025
• Update README.md to note newer NVIDIA GPUs by @jeffklassen in #3031
• ruby: use CMake in build process by @KitaitiMakoto in #3043
• examples : add FFmpeg v7.0 support to ffmpeg-transcode.cpp by @fujimotos in #3038
• feat: Add no-context option to server by @sachaarbonel in #3045
• ruby : make Ruby bindings installed with build options by @KitaitiMakoto in #3056
• examples : add HEAPU8 to exported runtime methods by @danbev in #3062
• ci : disable freeBSD job in build.yml by @danbev in #3064
• coreml : set convert_to="mlprogram" in convert by @danbev in #3060
• sync : ggml by @ggerganov in #3071
• ci : enable bindings java job by @danbev in #3070
• ruby : add encoder begin callback related methods by @KitaitiMakoto in #3076
• Fix deprecated FFmpeg functions by @Podre-Henrique in #3073
• Add Moore Threads GPU support and update GitHub workflow for MUSA build by @yeahdongcn in #3069
• ci : disable publishing of java binding [no ci] by @danbev in #3086
• talk-llama : sync llama.cpp by @ggerganov in #3084
• whisper : remove empty .gitmodules file [no ci] by @danbev in #3085
• feat: expose language detection probabilities to server example by @sachaarbonel in #3044
• whisper : fix grammar advance stack warning by @danbev in #3087
• ggml : suppress Windows compiler warnings by @danbev in #3075
• make : fix samples glob pattern by @ggerganov in #3100
• ruby : ignore "Downloading" output in test_log_suppress by @danbev in #3106
• server : add --no-gpu option to print usage output by @danbev in #3098
• whisper : add check that target name exists by @danbev in #3103
• sync : ggml by @ggerganov in #3108
• ruby : refine HTTP cache feature by @KitaitiMakoto in #3109
• feat(server): bump httplib.h to version 0.20.0 by @sachaarbonel in #3101
• removed stdc++fs by @JaredTweed in #3097
• docs : Update cli documentation by @antimatter96 in #3102
• cli : Support "-" for stdout like stdin by @danielzgtg in #3050
• feat(server): Improve HTTP Connection Abort Handling by @sachaarbonel in #3112
• whisper: remove MSVC warnings pragmas by @danbev in #3090
• ci : add zip extension to xcframework artifact name by @danbev in #3120
• ci : zip windows artifacts for release uploading by @danbev in #3124
• sync : ggml by @ggerganov in #3125
• ci : add bindings-java jar artifact to release by @danbev in #3126
• sync : ggml by @ggerganov in #3127
• stream.wasm : add HEAPU8 to exported runtime methods by @danbev in #3130
• whisper : deprecate WHISPER_CCACHE CMake option by @danbev in #3131
• wasm : add note about worker.js file generation [no ci] by @danbev in #3133
• examples : add HEAPU8 to all of the exported runtime methods by @enesgrahovac in #3134
• ruby : omit test_build_options locally by @danbev in #3132
• ruby : test extra build options only when env var specified by @KitaitiMakoto in #3136
• examples : update link to Paul Tol's color scheme [no ci] by @danbev in #3140
• Update Readme to recommend same Openvino as Python tools by @peardox in #3138
• cli : print color scheme info for --print-colors by @danbev in #3141
• docs : fix -owts flag typo karaoke section [no ci] by @danbev in #3142
• whisper : remove dummy commit comment [no ci] by @danbev in #3143
• vad : add initial Voice Activity Detection (VAD) support by @danbev in #3065
• docs: Update README.md for whisper.objc app by @tomer-schles in #2569
• vad : remove shortform for --vad option in cli.cpp by @danbev in #3145
• examples : add VAD speech segments example by @danbev in #3147
• sync : ggml by @ggerganov in #3148
• server : add --flash-attn usage output by @danbev in #3152
• vad : add download-vad-model scripts by @danbev in #3149
• examples : add --print-confidence option to cli by @danbev in #3150
• whisper : add build_*/ to .gitignore [no ci] by @danbev in #3157
• vad : store VAD context in whisper_state by @danbev in #3156
• vad : return early if no vad segments are detected by @danbev in #3158
• examples : add vad-speech-segments to win warns [no ci] by @danbev in #3170
• sync : ggml by @ggerganov in #3171
• ruby : add GGML_SYCL_DNN option to ruby bindings by @danbev in #3172
• Fix CMakeLists.txt to handle deprecated gpu Warnings by @jugal-sheth in #3163
• whisper : remove redundant assignments by @danbev in #3178
• docs: fix very minor typo in README by @alpaim in #3179
• docs : add VAD model download instructions [no ci] by @danbev in #3180
• feat(server): Add k6 Load Testing Script by @sachaarbonel in #3175
• ci : use dynamic libopenblas.dll for window-blas by @danbev in #3177
• docs : Fix VAD section heading levels in README by @KitaitiMakoto in #3186
• Quickfix for swedish umlauts + expose model inference settings in talk-llama.cpp by @matteng1 in #3187
• node : enable no_prints to suppress all output by @danbev in #3189
• docs : convert README_sycl.md to utf8 format [no ci] by @danbev in #3191
• sync : ggml by @ggerganov in #3193
• ci : update windows artifact uploads steps by @danbev in #3192
• tests : add a new benchmark test for long-form audio by @fujimotos in #3185
• Install shared libs when using GGML_BACKEND_DL by @peardox in #3195
• ruby : add VAD support, migration to Ruby's newer API by @KitaitiMakoto in #3197
• whisper : remove whisper_load_backends function by @danbev in #3196
• sync : ggml by @ggerganov in #3202
• ggml : Fix backtrace breaking Windows build by @danielzgtg in #3203
• ruby : handle build options on installation by @KitaitiMakoto in #3206
• vad : revisit timestamp alignment/mapping by @danbev in #3173
• ruby : add Core ML support by @KitaitiMakoto in #3214
• sync : ggml by @ggerganov in #3215
• node : add language detection support by @danbev in #3190
• ci : use mirrors.kernel.org for Ubuntu packages by @danbev in #3220
• musa: correct MUSA SDK rc4.0.1 download URL by @yeahdongcn in #3217
• fix: apply whisperParams in fullTranscribeWithTime by @Jo4sDev in #3201
• ci : add mirror for ports.ubuntu.com (ARM packages) by @danbev in #3221
• ruby : Add parallel transcription support by @KitaitiMakoto in #3222
• devops: add main-intel dockerfile by @kwaa in #3229
• ci(docker): build and publish main-intel image by @kwaa in #3231
• ruby : output format by @KitaitiMakoto in #3237
• sync : whisper.cpp by @ggerganov in #3239
• ruby : add cleaning of library names in dependencies by @danbev in #3241
• ci : update windows runner to windows-2022 by @danbev in #3242
• ruby : add .gitignore entries for ext directory by @danbev in #3245
• cli : fix short name conflict for vad options [no ci] by @danbev in #3247
• server : add Voice Activity Detection (VAD) support by @danbev in #3246
• whisper : fix VAD processing for skipped audio segments by @danbev in #3230
• feat(server): graceful shutdown, atomic server state, and health endpoint Improvements by @sachaarbonel in #3243
• let people select the model the wanna use with yt-wsp.sh using a second argument by @w1redch4d in #3251
• examples : set the C++ standard to C++17 for server by @danbev in #3261
• whisper : clear result_all if vad_samples is empty by @danbev in #3262
• sync : ggml by @ggerganov in #3264
• examples : add stereo to mono conversion in read_audio_data by @danbev in #3266
• cmake : fix android build by @ggerganov in #3265
• android : update CMakeLists.txt to use FetchContent for ggml by @danbev in #3268
• sync : ggml by @ggerganov in #3272
• ruby : specify Apple frameworks explicitly on build by @KitaitiMakoto in #3270
• ci : add apt-get clean to musa Dockerfile by @danbev in #3275
• whisper-command: write commands to text file by @aaron-ang in #3273
• chore: add .gitignore entries for OpenVINO support by @mochiya98 in #3276
• ci : reduce musa image size by @danbev in #3277
• backport CoreML features to macos < 14 by @glaszig in #3255
• feat: update java example by @Jo4sDev in #3281
• ci : enable main-cuda build by @danbev in #3282
• stream : add nullptr check of whisper_context by @danbev in #3283

New Contributors

• @fujimotos made their first contribution in #3002
• @gregsadetsky made their first contribution in #3006
• @Olli made their first contribution in #3016
• @ekaitz-zarraga made their first contribution in #3024
• @jeffklassen made their first contribution in #3031
• @Podre-Henrique made their first contribution in #3073
• @yeahdongcn made their first contribution in #3069
• @JaredTweed made their first contribution in #3097
• @antimatter96 made their first contribution in #3102
• @danielzgtg made their first contribution in #3050
• @enesgrahovac made their first contribution in #3134
• @peardox made their first contribution in #3138
• @tomer-schles made their first contribution in #2569
• @jugal-sheth made their first contribution in #3163
• @alpaim made their first contribution in #3179
• @matteng1 made their first contribution in #3187
• @Jo4sDev made their first contribution in #3201
• @kwaa made their first contribution in #3229
• @w1redch4d made their first contribution in #3251
• @aaron-ang made their first contribution in #3273
• @mochiya98 made their first contribution in #3276
• @glaszig made their first contribution in #3255

Full Changelog: v1.7.5...v1.7.6