Spaces:
Running
Running
Commit History
whisper : support speaker segmentation (local diarization) of mono audio via tinydiarize (#1058) eedbf0c unverified
talk-llama : fix new rope interface 982cdf8 unverified
Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)" 1e5ddb0 unverified
ggml : sync latest repo (mostly refactoring changes) d97fd69 unverified
talk-llama : fix build on macOS (#1062) 15d6fd8 unverified
Przemysław Pawełczyk commited on
extra : update 'quantize-all.sh' to quantize all downloaded models (#1054) b2215ea unverified
thefinaldegree commited on
whisper : `split_on_word` no longer trims (#1046) 2b07302 unverified
ggml : do not use _GNU_SOURCE gratuitously (#1027) 3a69cdf unverified
Przemysław Pawełczyk commited on
talk-llama : fix build after ggml sync (#1049) 4dcdfda unverified
Przemysław Pawełczyk commited on
metal : sync ggml-metal (ref #1047) 799974c unverified
opencl : sync latest ggml-opencl ced3ca3 unverified
whisper : fix build with -Werror=undef (#1045) 29932e6 unverified
Philippe Normand commited on
models : add ggml_to_pt script (#1042) 95e087e unverified
models : cd statements are quoted to allow spaces in path (#1041) 3063d29 unverified
Roddur Dasgupta commited on
models : handle paths with spaces in download script (close #1038) 097a82d unverified
main : add diarization support for all current output types (#1031) 16846f8 unverified
readme : add java alternative binding (#1029) 1b58b55 unverified
GiviMAD commited on
go : add support for whisper_full_lang_id() (#1010) 1d4bf86 unverified
go : fix "cb" -> "callNewSegment" cdb726d unverified
ggml : sync latest ggml lib a100c9a unverified
go : improve progress reporting and callback handling (#1024) 19d7f69 unverified
make : update cuBLAS build both x86 and aarch64 (#1015) 5d4a28f unverified
byte-6174 commited on
make : fix for CUDA native not working as an option on Ubuntu (#1012) 1807a31 unverified
KP Kaiser commited on
main : exit gracefully when invalid params are passed 3706d35 unverified
main : gracefully exit when invalid params are passed (#1002) 951f044 unverified
py : make convert-pt-to-ggml.py backwards compatible with older vocab.json tokenizer files (#1001) 83e4988 unverified
readme : corrected syntax for markdown link (#995) 2aebdfc unverified
Larry Battle commited on
updated java README 465bc94
`speak` scripts for Windows 2fdd855
updated README for java 84f8053
whisper.android : support decode wav file has 2 channels (#972) 1771dce unverified
Feature/java bindings2 (#944) 66cb305 unverified
models : fix README.md (#964) 9cc4aaa unverified
genevera (she/her) commited on
examples : update elevenlabs scripts to use official python API (#837) ed6d1a3 unverified
DGdev91 commited on
readme : highlight OpenBLAS support (#956) ee7503d unverified
0xsourcecode commited on
talk-llama : sync latest llama.cpp (close #922, close #954) ad4065a unverified
cmake : build with any BLAS compatible library (#927) 1fe6df0 unverified
ggml : update WASM SIMD 84c1cc7 unverified
ggml : sync latest ggml repo 6ee8740 unverified
bindings : add java bindings (#931) 3b6a58b unverified
whisper : fix hebrew language code (#935) 828e876 unverified
coreml : add support of large-v1 model (#926) 7935008 unverified
Ahmad Bilal commited on
release : v1.4.2 92d863e unverified
ggml : add AVX dot products 7e7b11c unverified
talk-llama : fix build + sync latest llama.cpp ef85c02 unverified
readme : improve Core ML model conversion guidance (#915) dd59682 unverified
coreml : support quantized model files 8831554 unverified
ggml : sync latest ggml 803e1be unverified
main : fix help for --no-timestamps arg (#908) 4ceb1ab unverified
Rich Jones commited on