Spaces:
Sleeping
Sleeping
Commit History
whisper : rename suppress_non_speech_tokens to suppress_nst (#2653) 5b0631d unverified
server : add option to suppress non-speech tokens (#2649) 647c7e7 unverified
whisper : rename binaries + fix install (#2648) 30197de unverified
android : try to fix build c9db590
files : remove old sources 1da9474
talk-llama : sync llama.cpp c4fb34c
common : remove old types fc4a926
stream : improve consistency in README (#2642) 91a639e unverified
crummyh commited on
common : add cstdio header ad1017f unverified
stream : update build instructions 19c0156 unverified
android : fix build and ci (#2624) 0025feb unverified
ci : disable CUDA and Android builds fcafd21
ci : disable Obj-C build + fixes 3859606
talk-llama : sync llama.cpp 5908a19
common : fix compile warning 6a0d528
whisper : adapt to new ggml (wip) ec6f374
talk-llama : sync llama.cpp 1568fc8
sycl: fix example build (#2570) a0dcffc unverified
Stefan Sydow commited on
whisper.swiftui : switch Mac dest to Mac (Designed for iPad) (#2562) 13f2beb unverified
build : fixes 11d19cb
talk-llama : sync llama.cpp 6bb34fb
whisper.swiftui : add model download list & bench methods (#2546) 5767578 unverified
examples : fix ffmpeg v5 build (#2543) 88b342e unverified
Stefan Sydow commited on
talk-llama : sync llama.cpp 8177527
whisper : add dtw preset for large-v3-turbo (#2481) eae3cdd unverified
objc : fix build 564bce1
whisper : adapt to latest ggml (skip) (#0) ad9dd7b
examples : update dr_wav.h to newer version (#2449) d678325 unverified
Rahul Vadhyar commited on
talk-llama : sync llama.cpp c9ddda2
server : ffmpeg overwrite leftover temp file (#2431) 2dafb8e unverified
whisper : add large-v3-turbo (#2440) f3283ba unverified
make : remove "talk" target until updated 5fb8fce
talk-llama : sync llama.cpp f91f98d
examples : adapt to ggml.h changes (ggml/0) 91c7734
server : use OS-generated temp file name for converted files (#2419) 04d9c8d unverified
readme : remove invalid flag from Python example (#2396) 5372e8b unverified
UsernamesLame commited on
talk-llama : sync llama.cpp 4493ffd
examples : use colorblind friendly TTY color scheme (#2360) 09303a2 unverified
Justine Tunney commited on
build : fix aarch64 (#0) 55befbb
talk-llama : sync llama.cpp a40d0a7
common : handle new quant types (ggml/0) 53bb541
talk-llama : sync llama.cpp 7ef5ccc
examples : fix compile warnings [no ci] (#0) 32cfce9
server : add inference path to make OAI API compatible (#2270) 66a3eb1 unverified
cmake : minor fixes 369b16c unverified
whisper : disable CUDA mel + fix FFMPEG 2831df8 unverified
whisper : reorganize source code + improve CMake (#2256) f75c2e3 unverified
talk-llama : sync llama.cpp e8e18fb unverified
move BLAS to a separate backend (cont) (llama/6210) 4b26445
slaren commited on