Spaces:
Running
Running
Commit History
whisper : fix "bench-all outputs an invalid result on larger models" (#3002) b6c9266 unverified
rename : ggerganov -> ggml-org (#3005) f816f88 unverified
coreml: fix Whisper to CoreML conversion by disabling SDPA [no ci] (#2979) bf862e4 unverified
whisper : remove unnecessary GGML_UNUSED macro (#2960) b2e42a5 unverified
whisper : add support for backends with multiple ggml_backend_buffer_type (#2863) 79fa7cf unverified
Dan Johansson commited on
whisper : initialize decoder's rng with unique seed (#2932) 6322856 unverified
whisper : add check for CPU backend initialization (#2918) ae8d838 unverified
whisper : fix compiler warnings in whisper.cpp (#2895) bfa2ae7 unverified
whisper : enable compiler warnings for src (#2891) a216359 unverified
whisper : support GGML_BACKEND_DL (#2843) 2e6437e unverified
whisper : restore big endian support (#2816) 7631e20 unverified
Thomas Fitzsimmons Xuan-Son Nguyen commited on
ci : dummy commit to trigger CI 600a548 unverified
whisper : fix gpu device selection (#2728) 87b427e unverified
whisper : add whisper_full_get_segment_no_speech_prob_from_state (#2716) cb32a92 unverified
Sandro Hanea commited on
server : add no-speech threshold parameter and functionality (#2654) 8e40db9 unverified
whisper : rename suppress_non_speech_tokens to suppress_nst (#2653) 5b0631d unverified
whisper : support no_speech_thold (#2625) adb5837 unverified
Karthick commited on
whisper : add single-timestamp logic (#2629) 7655c06 unverified
whisper : use backend registry (#0) b9f5e40
whisper : adapt to new ggml (wip) ec6f374
whisper : fix build (#0) dfd316d
whisper.swiftui : add model download list & bench methods (#2546) 5767578 unverified
ggml : vulkan logs (#2547) aec2a89 unverified
thewh1teagle commited on
whisper : fix extra memory usage (#2534) 96efeba unverified
whisper : backend registry init before model load 606cb52
ggml : alloc ggml_contexts on the heap (#2525) 3ccf40a unverified
whisper : minor compile warning c06d5f9 unverified
whisper : move new-segment callback after DTW step (#2515) 6b8369d unverified
whisper : fix index overflow in token-level timestamp logic (#2505) de79ec1 unverified
whisper : add dtw preset for large-v3-turbo (#2481) eae3cdd unverified
whisper : add OpenVINO init with state (#2464) 6d5166f unverified
Sandro Hanea Sandro Hanea commited on
whisper : zero-out the KV cache upon clear (#2445) b8af443
whisper : revert mel-related changes (#0) 7708c26
whisper : adapt to latest ggml (skip) (#0) ad9dd7b
whisper : fix excessive memory usage (#2443) afe3785 unverified
talk-llama : sync llama.cpp c9ddda2
talk-llama : sync llama.cpp f91f98d
ggml : refactoring (llama/#0) 1b62c96
whisper : update FA call 2bfec97
whisper : fix compile warning for unused params 0e05e03 unverified
cann : add Ascend NPU support (#2336) 94baae9 unverified
whisper : fix compile warning (#0) 1a699ea
cmake : fix compile in xcode (#2311) c0c60f1 unverified
Daven Sanassy commited on
whisper : handle empty mel (#2324) 1434bfe unverified
whisper : use vulkan as gpu backend when available (#2302) 0755fa0 unverified
Matt Stephenson commited on
whisper : fix DTW assert (#2299) 1d1d815 unverified
arizhih commited on