Spaces:
Sleeping
Sleeping
Commit History
release : v1.5.1
4515273
unverified
metal : add backend function to check device family support (#1547)
c95e649
unverified
cuda : sync some minor stuff from llama.cpp (#1548)
cc06e31
unverified
whisper : fix typo
c692ba5
unverified
server : add --print-realtime param (#1541)
83982ec
unverified
ecneladis
commited on
whisper : add whisper_lang_str_full (#1546)
904280f
unverified
fix(server): typo in temperature parameter (#1545)
91e39cd
unverified
Okabintaro
commited on
metal : fix build (#1544)
02dbf1a
unverified
sandrohanea
commited on
readme : add server example
544bef6
unverified
Change temp file name for server application (#1535)
531cbf9
unverified
bench : pass memcpy threads from cli
027d207
unverified
bench : multi-thread memcpy (#1534)
c0ee6b3
unverified
Close file after writing in server application (#1533)
3217f72
unverified
server : add video to readme
456ddab
unverified
whisper : update example in whisper.h (#1529)
5a48cf5
unverified
M. A. Ali
commited on
sdl : fix audio callback (#1523)
cd7b137
unverified
whisper : reuse whisper_decode_with_state (#1521)
5938aed
unverified
ci : redistribute CUDA DLLs (#1522)
aaab0d5
unverified
Tamotsu Takahashi
commited on
whisper : fix with_state methods to use the correct state (#1519)
2b4a95c
unverified
sandrohanea
Sandro Hanea
commited on
whisper : fix overriding the audio context
d717a20
unverified
cuda : assert ggml_add sources to be contiguous
c012035
unverified
ios : sync submodule
c0b01ea
unverified
sync : ggml (ggml-alloc + linker + gguf fixes) (#1501)
58507b9
unverified
quantize : add support for K-quant types
91ed6bd
unverified
bench : fix memcpy bench size
97246e8
unverified
talk-llama : improve quote and backtick handling (#1364)
fa6a8a8
unverified
Sam Pullara
commited on
talk-llama : enable GPU by default
afd6523
unverified
models : add info about distilled models
8c251e2
unverified
release : v1.5.0
65d366a
unverified
bench-all : add distil models
09d2496
unverified
js : latest whisper.js
4b2fe60
unverified
bench-all : indentations
92df795
unverified
whisper : make large version explicit + fix data size units (#1493)
03a3210
unverified
java : fix test (#1492)
d6276a7
unverified
whisper : add batched decoding (#1486)
0131aa6
unverified
java : use tiny.en for tests (#1484)
d03f526
unverified
whisper : add grammar-based sampling (#1229)
46f0c56
unverified
talk-llama : add n_gpu_layers parameter (#1475)
aa7c2e9
unverified
examples : add whisper.android.java for compatibility with older Android versions using Java (#1382)
bb48f57
unverified
Tong Li
litongmacos
bobqianic
commited on
readme : update comment about source code
730c424
unverified
ggml : fix some compile warnings
ad6c9c1
unverified
readme : update GPU / CUDA
e8ad308
unverified
whisper : add full CUDA and Metal offloading (#1472)
da4acca
unverified
whisper : return with error from whisper_encode_internal and whisper_decode_internal when abort callback is true (#1456)
ca0dc29
unverified
talk-llama : add language auto detect (#1467)
cfc50d3
unverified
openvino : update convert-whisper-to-openvino.py to support v3 (#1459)
b9f3d1b
unverified
bobqianic
commited on
