cmake : Fix bug in httplib.h for mingw (#1615)

metal : fix `ggml_metal_log` vargs (#1606)

whisper.objc : disable timestamps for real-time transcription

whisper : more debug messages + fix fallback logic

metal : fix soft_max kernel src1 argument (#1602)

sync : ggml (new ops, new backend, etc) (#1602)

server : pass max-len argument to the server (#1574)

ios : Remove `#if arch(arm)` check for using Metal (#1561)

ggml : Fix 32-bit compiler warning (#1575)

ggml : re-enable blas for src0 != F32 (#1583)

Server : Add support for .vtt format to Whisper server (#1578)

server : backport .srt output format (#1565)

cmake : install required ggml.h header (#1568)

server : set default CORS headers to allow all (#1567)

readme : update help (#1560)

CI : Add CUDA 11.8.0 support (#1554)

CI : Rectify the Clang-Related workflow issues (#1551)

server : automatically convert audio on the server (#1539)

whisper : remove trailing whitespaces

release : v1.5.1

metal : add backend function to check device family support (#1547)

cuda : sync some minor stuff from llama.cpp (#1548)

whisper : fix typo

server : add --print-realtime param (#1541)

whisper : add whisper_lang_str_full (#1546)

fix(server): typo in temperature parameter (#1545)

metal : fix build (#1544)

readme : add server example

go : fixed Makefile for MacOS ARM 64 (#1530)

Change temp file name for server application (#1535)

bench : pass memcpy threads from cli

bench : multi-thread memcpy (#1534)

Close file after writing in server application (#1533)

server : add video to readme

server : add a REST Whisper server example with OAI-like API (#1380)

whisper : update example in whisper.h (#1529)

sdl : fix audio callback (#1523)

whisper : reuse whisper_decode_with_state (#1521)

ci : redistribute CUDA DLLs (#1522)

whisper : fix with_state methods to use the correct state (#1519)

whisper : fix overriding the audio context

cuda : assert ggml_add sources to be contiguous

ios : sync submodule

sync : ggml (ggml-alloc + linker + gguf fixes) (#1501)

quantize : add support for K-quant types

bench : fix memcpy bench size

talk-llama : improve quote and backtick handling (#1364)

talk-llama : enable GPU by default

models : add info about distilled models

release : v1.5.0