whisper : reorganize source code + improve CMake (#2256)

whisper : remove `speed_up` and `phase_vocoder*` functions (#2198)

whisper : use flash attention (#2152)

readme : add Fedora dependencies (#1970)

talk, talk-llama : pass text_to_speak as a file (#1865)

examples : initialize context params properly (#1852)

sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677)

whisper : add full CUDA and Metal offloading (#1472)

whisper : add context param to disable gpu (#1293)

examples: Update the README for Talk - fixing the gpt2 URL (#1334)

build : do not use _GNU_SOURCE gratuitously (#1129)

examples : fix build + compile warnings (close #1256)

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220)

Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)"

ggml : do not use _GNU_SOURCE gratuitously (#1027)

`speak` scripts for Windows

examples : update elevenlabs scripts to use official python API (#837)

whisper : add integer quantization support (#540)

whisper : add GPU support via cuBLAS (#834)

talk, talk-llama : add basic example script for eleven-labs tts (#728)

talk-llama : add new example + sync ggml from llama.cpp (#664)

models : change HF hosting from dataset to model

examples : refactor in order to reuse code and reduce duplication (#482)

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

cmake : update to 3.19 (#351)

examples : fix memory leak on failure to load gpt2 model (#323)

examples : small code cleanups (#322)

cmake : enable and fix -Wall -Wextra -Wpedantic C++ warnings

talk : improve prompting

talk : make compatible with c++11 (part 2)

talk : make compatible with c++11

Update README.md

talk : fix build for MSVC

talk : talk with AI in the terminal