whisper : clear result_all if vad_samples is empty (#3262)

whisper : fix VAD processing for skipped audio segments (#3230)

vad : revisit timestamp alignment/mapping (#3173)

whisper : remove whisper_load_backends function (#3196)

whisper : remove redundant assignments (#3178)

vad : return early if no vad segments are detected (#3158)

vad : store VAD context in whisper_state (#3156)

whisper : update to ggml-backend changes (#0)

vad : add initial Voice Activity Detection (VAD) support (#3065)

whisper : remove dummy commit comment [no ci] (#3143)

whisper: remove MSVC warnings pragmas (#3090)

whisper : fix grammar advance stack warning (#3087)

whisper : reduce delta_min from 1000ms to 100ms (#3028)

whisper : fix "bench-all outputs an invalid result on larger models" (#3002)

rename : ggerganov -> ggml-org (#3005)

coreml: fix Whisper to CoreML conversion by disabling SDPA [no ci] (#2979)

whisper : remove unnecessary GGML_UNUSED macro (#2960)

whisper : add support for backends with multiple ggml_backend_buffer_type (#2863)

whisper : initialize decoder's rng with unique seed (#2932)

whisper : add check for CPU backend initialization (#2918)

whisper : fix compiler warnings in whisper.cpp (#2895)

whisper : enable compiler warnings for src (#2891)

whisper : support GGML_BACKEND_DL (#2843)

whisper : restore big endian support (#2816)

ci : dummy commit to trigger CI

whisper : fix gpu device selection (#2728)

whisper : add whisper_full_get_segment_no_speech_prob_from_state (#2716)

server : add no-speech threshold parameter and functionality (#2654)

whisper : rename suppress_non_speech_tokens to suppress_nst (#2653)

whisper : support no_speech_thold (#2625)

whisper : add single-timestamp logic (#2629)

whisper : use backend registry (#0)

whisper : adapt to new ggml (wip)

whisper : fix build (#0)

whisper.swiftui : add model download list & bench methods (#2546)

ggml : vulkan logs (#2547)

whisper : fix extra memory usage (#2534)

whisper : backend registry init before model load

ggml : alloc ggml_contexts on the heap (#2525)

whisper : minor compile warning

whisper : move new-segment callback after DTW step (#2515)

whisper : fix index overflow in token-level timestamp logic (#2505)

whisper : add dtw preset for large-v3-turbo (#2481)

whisper : add OpenVINO init with state (#2464)

whisper : zero-out the KV cache upon clear (#2445)

whisper : revert mel-related changes (#0)

whisper : adapt to latest ggml (skip) (#0)

whisper : fix excessive memory usage (#2443)

talk-llama : sync llama.cpp

talk-llama : sync llama.cpp