whisper : do not provide past prompt when n_max_text_ctx == 0

wasm : check if navigator.storage.estimate() is available

go : added wrappers to reset and print timings (#436)

ci : run workflows on pull requests + bindings depend on .h (#446)

whisper.wasm : add labels for easier radio selection (#435)

whisper : condition timestamps to be monotonically increasing (#425)

whisper : PPC64 big-endian support (#398)

release : v1.1.1

.gitignore : add arm_neon.h

whisper : fix condition for providing past prompt (critical)

whisper : extend information in whisper_print_timings()

whisper : perform entropy check only when we have at least 32 tokens (#412)

main : we had accidentally disabled the temperature fallback .. (#291)

whisper.wasm : add small and small.en models

bench : minor fixes

main : add an option to accept optional output filenames (#424)

stream : fix handling of --step == --length (#416)

bench : fix Windows linkage by moving ggml benches in whisper lib ..

bench : add memcpy and ggml_mul_mat benchmarks

whisper.android : add support for loading directly from asset in C (#415)

whisper : fix possible uninitialized variables (#291)

stream : fix --keep_context argument to be used correctly (#354)

go : remove sample_best and sample_timestamp bindings (#409)

Update README.md

cmake : bump version to 1.1.0

Update README.md

whisper : account speed_up flag for short audio (close #405)

Update README.md

bench.wasm : print system info

Improve decoding (#291)

stream : fix a bug that inserted a lot of empty audio at the start

ggml : remove obsolete zeroing + comment fixes (#390)

readme : clarify main and stream usage (#391)

ggml : correct behaviour of ggml_vec_sum_f32 (#390)

whisper : fix sample_to_timestamp calculation with 64 bit precision to avoid overflow (#388)

whisper : add loader class to allow loading from buffer and others (#353)

ggml : improve vec_dot_f16 unrolling in flash_attn_f16

command : clean-up / refactoring / formatting (#383)

command : always-prompt mode (#383)

go : adding features to the go-whisper example, go ci, etc (#384)

ggml : fix bug in new soft max computation

cmake : add -Wno-unused-function + update whisper.js

ggml : when using BLAS start only 1 CPU thread

ggml : fix running tasks with variable number of threads

ggml : unroll ggml_vec_dot_f16 in ggml_compute_forward_flash_attn_f16

whisper : revert accidental MB change

ggml : speed-up soft max via Accelerate + unroll

ggml : use vDSP_sve and vDSP_maxv from Accelerate

ggml : make gcc happy (minor)

talk.wasm : bump memory usage + update whisper.js