Spaces:
Sleeping
Sleeping
Commit History
-
whisper : fixed crash in GPU device selection on multi-GPU systems (#3372)
Unverified signature0869200
-
whisper : reset conv scheduler when CoreML is used (#3350)
Unverified signatureggml-cif425556
-
whisper: validate get_rows support for cpu extra buffer (#3323)
Charles XuUnverified signature3c6ba32
-
whisper : add version function (#3289)
Unverified signature* whisper : add version function This commit adds a version function to the whisper API. The motivation for this is that it might be convenient to have a way to programmatically check the version. Example usage: ```c++ printf("Using whisper version: %s\n", whisper_version()); ``` Will output: ```console Using whisper version: 1.7.6 ``` * examples : add version to android example CMakeLists.txt0b952d7
-
coreml : backport CoreML features to macos < 14 (#3255)
glaszigUnverified signaturedc0917f
-
whisper : clear result_all if vad_samples is empty (#3262)
Unverified signatureThis commit clears the results_all vector no VAD segments are found. The motivation for this is that this would normally be done by `whisper_full_with_state` but when no VAD segments are detected this current implementation does not call that function and hence the vector does not get reset. This can lead to issues in applications like the server example where it will incorrectly process the old results. Resolves: https://github.com/ggml-org/whisper.cpp/issues/325060ecd84
-
whisper : fix VAD processing for skipped audio segments (#3230)
Unverified signatureThis commit addresses an issue with token timestamps when audio segments are skipped, in `whisper_exp_compute_token_level_timestamps` related to the VAD processing and the energy levels. The motivation for this is that the token timestamps exceed the energy array bounds due to segment timing misalignment: ```console (skipped introduction) ↓ Audio segment: [2600ms → 5600ms] (3 seconds of actual audio) Energy array: [0 → 480652] (samples for 3 seconds) Token timestamps: [3266ms → 3408ms] (absolute timestamps) ``` So both `s0` and `t1` get clamped to the maximum sample index (480652) which causes the start/end timestamps to be the same for all the tokens after a certain point. This is addressed by using segment-relative timestamps in the `timestamp_to_sample` and `sample_to_timestamp`.a69c121
-
vad : revisit timestamp alignment/mapping (#3173)
Unverified signature* vad : revisit timestamp alignment/mapping This commit improving the timestamp alignment by introducing a mapping table, adding intermediate reference points for longer segments, and binary search for lookups. The motivation for this changes is to address issues with the currently solution where zero-length segments are possible, and also to improve the precision of the VAD timestamps. Refs: https://github.com/ggml-org/whisper.cpp/issues/3162 * vad : use uint64_t for time mapping This commit changes the type of the `processed_time` and `original_time` fields in the `vad_time_mapping` struct from `double` to `uint64_t`. The motivation for this change is made to improve precision and avoid floating-point inaccuracies and also be consistent with other part of the code base that use `uint64_t` for time representation. This is a part of a refactoring where I'm also going to change the vad_segment_info struct to use `uint64_t` for the start and end times. This is the reason for the n…f198f02
-
whisper : remove whisper_load_backends function (#3196)
Unverified signature* whisper : remove whisper_load_backends function This commit removes the `whisper_load_backends` function, which was used to load all GGML backends. The motivation for this change push the responsibility of loading backends to user applications to give them more control over which backends to load and when. See the references below for more context. Resolves: https://github.com/ggml-org/whisper.cpp/issues/3182 Refs: https://github.com/ggml-org/whisper.cpp/pull/3042#issuecomment-2801778733 Refs: https://github.com/ggml-org/whisper.cpp/pull/3042#issuecomment-2801928990 * ruby : add check for rwc is NULL This commit adds a check to ensure that the `rwc` pointer is not NULL before attempting to mark its members in the garbage collector. The motivation for this is an attempt to see if this fixed the CI build as I'm not able to reproduce the issue locally. Refs: https://github.com/ggml-org/whisper.cpp/actions/runs/15299612277/job/43036694928?pr=31960cae2d6
-
whisper : remove redundant assignments (#3178)
Unverified signatureThis commit removes some redundant assignments in the function `whisper_exp_compute_token_level_timestamps`. The motivations for this is that tokens[j] and token are references to the same object and this can be a little confusing when reading the code.ec40497
-
vad : return early if no vad segments are detected (#3158)
Unverified signatureThis commit adds a check to `whisper_full_with_state` and if no VAD segments are detected, the function will return early. The motivation for this is that if no VAD segments are detected, the function will not have any samples to process which can happen if an audio sample does not contain any speech. I did not test this previously and only discovered this when updating the stream example.a28f11e -
vad : store VAD context in whisper_state (#3156)
Unverified signature* vad : store VAD context in whisper_state This commit stores the VAD context in the whisper_state structure, allowing for better management and reuse of the VAD context across multiple calls to the whisper_vad function. The motivation for this change is that when updating the stream example I noticed that the VAD context was being re-initialized every time the whisper_vad function was called. This involved loading the VAD model which is expensive and unnecessary if the context can be reused. Storing this in the whisper_state seems follow the pattern simliar to how whisper_coreml_context and whisper_openvion_context are stored. * vad : free vad_context in whisper_free_state821d05f
-
whisper : update to ggml-backend changes (#0)
ggml-cib12517c
-
vad : add initial Voice Activity Detection (VAD) support (#3065)
Unverified signature* vad : add initial Voice Activity Detection (VAD) support This commit add support for Voice Activity Detection (VAD). When enabled this feature will process the audio input and detect speech segments. This information is then used to reduce the number of samples that need to be processed by whisper_full. Resolves: https://github.com/ggml-org/whisper.cpp/issues/3003 --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>a28f35e -
whisper : remove dummy commit comment [no ci] (#3143)
Unverified signatureThis commit removes a dummy comment that was add by Commit(589b408 "ci : dummy commit to trigger CI").cac1a97
-
whisper: remove MSVC warnings pragmas (#3090)
Unverified signature* ggml : remove MSVC warnings pragmas This commit removes the MSVC-specific pragmas as these are now handled in CMakeLists.txt. * whisper : remove MSVC warning pragmas This commit removes the MSVC-specific pragmas. These are now handled in the CMakeLists.txt file.e0d130c
-
whisper : fix grammar advance stack warning (#3087)
Unverified signatureThis commit addresses a warnings that is present for Release builds: ```console [ 30%] Building CXX object src/CMakeFiles/whisper.dir/whisper.cpp.o In file included from /usr/include/c++/13/bits/stl_tree.h:63, from /usr/include/c++/13/map:62, from /home/danbev/work/ai/whisper.cpp/src/whisper-arch.h:5, from /home/danbev/work/ai/whisper.cpp/src/whisper.cpp:2: In static member function ‘static void std::__copy_move<false, false, std::random_access_iterator_tag>::__assign_one(_Tp*, _Up*) [with _Tp = const whisper_grammar_element*; _Up = const whisper_grammar_element* const]’, inlined from ‘static _Up* std::__copy_move<_IsMove, true, std::random_access_iterator_tag>::__copy_m(_Tp*, _Tp*, _Up*) [with _Tp = const whisper_grammar_element* const; _Up = const whisper_grammar_element*; bool _IsMove = false]’ at /usr/include/c++/13/bits/stl_algobase.h:440:20, inlined from ‘_OI std::__copy_move_a2(_II, _II, _OI) [with bool _IsMove = false; …e4a0565
-
whisper : reduce delta_min from 1000ms to 100ms (#3028)
Unverified signatureggml-cid3e767a
-
whisper : fix "bench-all outputs an invalid result on larger models" (#3002)
Unverified signatureThe benchmark script 'scripts/bench-all.sh' assumes that the 11th field of the output line is a timestamp. This assumption does not hold when the target model takes a bit longer to process. Fix this issue by introducing an explicit whitespace to the output lines of `whisper_print_timings()`. Signed-off-by: Fujimoto Seiji <fujimoto@ceptord.net>b6c9266 -
rename : ggerganov -> ggml-org (#3005)
Unverified signaturef816f88
-
coreml: fix Whisper to CoreML conversion by disabling SDPA [no ci] (#2979)
Unverified signature* coreml: fix Whisper to CoreML conversion by disabling SDPA This commit disables the use of PyTorch's `scaled_dot_product_attention` in the Whisper model to avoid compatibility issues during CoreML conversion. The issue occurs because coremltools requires PyTorch 2.5.0, but the Whisper implementation may expect behavior from newer PyTorch versions. By setting `MultiHeadAttention.use_sdpa = False`, we force Whisper to use its fallback manual attention implementation, which works correctly with PyTorch 2.5.0 during the tracing process. Refs: https://github.com/ggerganov/whisper.cpp/issues/2783 * coreml: fix audio shape in whisper decoder conversion This commit fixes the audio shape in the whisper decoder conversion script. The motivation for this is that the audio shape was incorrect and was causing the conversion to fail. * coreml : set -e in generate-coreml-interface.sh The commit sets the -e flag in the generate-coreml-interface.sh script to make sure the script fails if any…bf862e4
-
whisper : remove unnecessary GGML_UNUSED macro (#2960)
Unverified signatureb2e42a5
-
whisper : add support for backends with multiple ggml_backend_buffer_type (#2863)
Dan JohanssonUnverified signature* whisper : add support for ggml_backend_buffer_type Signed-off-by: Dan Johansson <dan.johansson@arm.com> * fix compile error when building on Ubuntu Signed-off-by: Dan Johansson <dan.johansson@arm.com> * remove copyright header from include file Signed-off-by: Dan Johansson <dan.johansson@arm.com> --------- Signed-off-by: Dan Johansson <dan.johansson@arm.com>79fa7cf
-
whisper : initialize decoder's rng with unique seed (#2932)
Unverified signatureThis change initializes each decoder's random number generator with a unique seed. The motivation for this is that currently all decoders are initialized with the same seed value, 0. The result of this is that for the same state (logits, probs, and logprobs) they will produce the same output.6322856
-
whisper : add check for CPU backend initialization (#2918)
Unverified signatureThis commit adds a check for the CPU backend initialization in the whisper library. If the initialization fails, an exception is thrown. The motivation for this change is to make the library more robust and handle the case when the CPU backend initialization fails. Resolves: https://github.com/ggerganov/whisper.cpp/issues/2917ae8d838
-
whisper : fix compiler warnings in whisper.cpp (#2895)
Unverified signatureThis commit fixes compiler warnings in whisper.cpp by changing the type of the loop index variable from int64_t to size_t. Currently the following warnings are generated by the compiler: ```console /whisper.cpp/src/whisper.cpp:209:27: warning: comparison of integers of different signs: 'int64_t' (aka 'long long') and 'size_t' (aka 'unsigned long') [-Wsign-compare] 209 | for (int64_t i = 0; i < nels; ++i) { | ~ ^ ~~~~ /whisper.cpp/src/whisper.cpp:219:27: warning: comparison of integers of different signs: 'int64_t' (aka 'long long') and 'size_t' (aka 'unsigned long') [-Wsign-compare] 219 | for (int64_t i = 0; i < nels; ++i) { | ~ ^ ~~~~ ```bfa2ae7 -
whisper : enable compiler warnings for src (#2891)
Unverified signature* whisper : enable compiler warnings for src This commit enables compiler warnings for the src directory. Currently when the WHISPER_ALL_WARNINGS flag is set to ON is only enables warnings in ggml, by setting GGML_ALL_WARNINGS to ON. This commit adds the same compiler flags for whisper's src directory. The motivation for this is to catch potential bugs and issues early on in the development process. * squash! whisper : enable compiler warnings for src Remove GF_C_FLAGS and GF_CXX_FLAGS from add_compile_options.a216359
-
whisper : support GGML_BACKEND_DL (#2843)
Diego Devesa +1: ggerganovUnverified signature* whisper : support GGML_BACKEND_DL * fix DTW crash * whisper.objc : fix build - add ggml-cpp.h --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>2e6437e
-
whisper : restore big endian support (#2816)
Thomas Fitzsimmons +1: Xuan-Son NguyenUnverified signature* whisper : fix BYTESWAP whitespace * whisper : make byteswap useable with C++17 * cmake : define WHISPER_BIG_ENDIAN for big-endian targets * ci : fix (again) arm64 build fails * docker : attempt fixing arm64 build on ci * qemu v7.0.0-28 [imported from https://github.com/ggml-org/llama.cpp /commit/818a340ea8be55b3706e1772527cb8738e90a8c7 (#11895)] --------- Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>7631e20
-
ci : dummy commit to trigger CI
Unverified signature600a548
-
whisper : fix gpu device selection (#2728)
Unverified signature87b427e
-
whisper : add whisper_full_get_segment_no_speech_prob_from_state (#2716)
Sandro HaneaUnverified signaturecb32a92
-
server : add no-speech threshold parameter and functionality (#2654)
Unverified signature8e40db9 -
whisper : rename suppress_non_speech_tokens to suppress_nst (#2653)
Unverified signature5b0631d
-
whisper : support no_speech_thold (#2625)
Unverified signature* Implement no_speech_thold no_speech_thold functionality is on par with OpenAI's whisper * Addressed review commentsadb5837 -
whisper : add single-timestamp logic (#2629)
Unverified signature* Fix hallucinations during silence When the predicted tokens end with a single timestamp the the entire 30 segment should be considered as done, to avoid hallucinations for the remaining part of segment. This behaviour is on par with openai's whisper. Refer to logic related to `single_timestamp_ending` in https://github.com/openai/whisper/blob/main/whisper/transcribe.py * Accept review comments related to formatting. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>7655c06
-
whisper : use backend registry (#0)
b9f5e40
-
whisper : adapt to new ggml (wip)
ec6f374
-
whisper : fix build (#0)
dfd316d
-
whisper.swiftui : add model download list & bench methods (#2546)
Unverified signature* swift : fix resources & exclude build * whisper : impl whisper_timings struct & api * whisper.swiftui : model list & bench methods * whisper : return ptr for whisper_get_timings * revert unnecessary change * whisper : avoid designated initializer * whisper.swiftui: code style changes * whisper.swiftui : get device name / os from UIDevice * whisper.swiftui : fix UIDevice usage * whisper.swiftui : add memcpy and ggml_mul_mat (commented)5767578 -
ggml : vulkan logs (#2547)
thewh1teagleUnverified signatureaec2a89
-
whisper : fix extra memory usage (#2534)
Vin Misra +1: vinmisraUnverified signature* passing samples_padded by ref to the threads. * passing samples_padded by ref to the threads. --------- Co-authored-by: Vinith Misra <physicsdemon@gmail.com>96efeba
-
whisper : backend registry init before model load
606cb52 -
ggml : alloc ggml_contexts on the heap (#2525)
Unverified signature* whisper : reduce ggml_context usage * ggml : allocate contexts on the heap (v2) * ggml : aligned malloc -> malloc3ccf40a
-
whisper : minor compile warning
Unverified signaturec06d5f9 -
whisper : move new-segment callback after DTW step (#2515)
Unverified signature6b8369d
-
whisper : fix index overflow in token-level timestamp logic (#2505)
Unverified signaturede79ec1
-
whisper : add dtw preset for large-v3-turbo (#2481)
Unverified signatureeae3cdd
-
whisper : add OpenVINO init with state (#2464)
Sandro Hanea +1: Sandro HaneaUnverified signature* Fixed OpenVino init on state * Removed an empty line * Fixed typo * Replaced tabs with spaces --------- Co-authored-by: Sandro Hanea <sandrohanea@users.noreply.github.com>6d5166f
-
whisper : zero-out the KV cache upon clear (#2445)
b8af443