common : separate whisper sources (#2846)

talk-llama : sync llama.cpp

talk-llama : sync llama.cpp (#2709)

talk-llama : sync llama.cpp

talk-llama : sync llama.cpp

examples : fix compile warnings [no ci] (#0)

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

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

whisper : use flash attention (#2152)

talk-llama : reject runs without required arguments (#2153)

talk-llama : sync llama.cpp

talk-llama : use llama_decode instead of llama_eval

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

talk-llama : sync llama.cpp

examples : initialize context params properly (#1852)

talk-llama : stream response (#1121)

talk-llama : optional wake-up command and audio confirmation (#1765)

talk-llama : add optional CLI arg to set the bot name (#1764)

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

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

talk-llama : enable GPU by default

talk-llama : add n_gpu_layers parameter (#1475)

talk-llama : add language auto detect (#1467)

talk-llama : fix n_gpu_layers usage again (#1442)

examples : fix n_gpu_layers usage in talk-llama (#1441)

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

sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)

talk-llama : update to latest llama.cpp

build : do not use _GNU_SOURCE gratuitously (#1129)

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

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

ggml : do not use _GNU_SOURCE gratuitously (#1027)

`speak` scripts for Windows

talk-llama : sync latest llama.cpp (close #922, close #954)

talk-llama : fix build + sync latest llama.cpp

talk-llama : fix session prompt load (#854)

talk-llama : add --session support (#845)

whisper : add integer quantization support (#540)

talk-llama : correct default speak.sh path (#720)

talk-llama : increase context to 2048

talk-llama : fixing usage message for talk-llama (#687)

talk-llama : add alpaca support (#668)

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