whisper : PPC64 big-endian support (#398)

bench : add memcpy and ggml_mul_mat benchmarks

go : bindings updated so they can be used in third party packages. (#379)

ggml : add SSE3 and fp16 conversion lookup table (#368)

minor : close #370 + Makefile build info print change

make : print build information

make : add i686 arch (close #329)

ggml : add f16 acceleration for POWER9 ppc64le

make : revert accidental change of optimization flags

main : add option to print the progress (#276)

talk : talk with AI in the terminal

make : indentation + .gitignore

Flag for Position Independent Code

fix compilation on haiku

models : add the new "large" model release by OpenAI

tests : adding transcription tests

Fix Darwin flags - was incorrectly always using the Linux else clause

examples : add "command" tool (#171)

correct model name display on running samples

add gprof option

fix AVX,AVX2,FMA,F16C detection on Linux and add flags for OpenBLAS

make : add libwhisper.so target (#144)

Check for AVX and AVX2 on Darwin

Allow building with Accelerate for x86_64 Macs (#123)

Cross compilation (#121)

refactoring : move main + stream in examples + other stuff

Update README.md and finalize the whisper.wasm example

added handling for falsely as x86_64 announced ARM Macs

Link Accelerate framework to "stream" example

Use Accelerate framework on Apple silicon

close #56 : build on FreeBSD

add static library make target

Fix Makefile for MacBook Intel

wip : rpi4 support

wip : improve makefile

Initial C-style interface for whisper.cpp

ref #10 : quick-and-dirty attempt for real-time audio transciption

Reduce memory usage even more + better sampling

Pass -pthread to linker

Flash + language support (ref #2)

ref #1 : add -pthread to compilation flags

Update README.md and simplify usage

Create README.md

Initial release