Spaces:
Sleeping
Sleeping
Commit History
ci : add cuBLAS build workflow and fix error causing lines in CMakeLists (#867) 4a2abaf unverified
readme : partial OpenCL GPU support via CLBlast (#863) 71b840c unverified
Vulcan commited on
build : CLBlast support as in llama.cpp (#862) 6a785f1 unverified
Vulcan commited on
ggml : fix 32-bit ARM build + quantization 87ee234
ggml : sync ggml (clBLAST + tensor names) f50d3b3 unverified
talk-llama : fix session prompt load (#854) 6eca3b7 unverified
Luis Herrera commited on
whisper : add detect-language mode (#853) 1251039 unverified
talk-llama : add --session support (#845) a7b3aa5 unverified
Luis Herrera commited on
bench : improve benchmarks d75ae65 unverified
whisper : add memory sizes for Q8_0 (close #846) 648dff8 unverified
whisper.wasm : fix typo in readme (#832) 1f461ff unverified
release : v1.4.1 8068ae8 unverified
whisper : fix quantize bug (#842) 6f45862 unverified
ggml : fix UB (int << 31) 8253b98 unverified
release : v1.4.0 a4c35c9 unverified
examples : fix + refactor Levenshtein distance 97f9410 unverified
whisper : add integer quantization support (#540) a5f8f3c unverified
whisper : add GPU support via cuBLAS (#834) d91d7d9 unverified
ggml : fix WASM build c3d7603 unverified
ggml : fix 32-bit ARM NEON (#836) 5fa72ca unverified
ggml : use vzip instead of vuzp for consistency 741db99 unverified
ggml : fix WASM build ada8c2d unverified
ggml : sync with ggml repo (warning fixes + asserts) caf2759 unverified
whisper : use correct seek_end when offset is used (#833) 44edc8a unverified
tests : add "threads" to run-tests.sh d880fda unverified
extra : add sync-ggml.sh script a899032 unverified
ggml : sync latest ggml + llama.cpp updates (quantization) ede1268 unverified
whisper.android : add some tips (#816) dd2c035 unverified
Zollner commited on
build : add WHISPER_COREML_ALLOW_FALLBACK to make / CMake (#812) 49fb1c6 unverified
whisper : allow non-CoreML fallback when Core ML cannot be loaded (#812) ebe63a9 unverified
Canis Lupus commited on
whisper : fix bug from previous commit 48b9b5d unverified
whisper : avoid designated initializers 5c76ae4 unverified
minor : improve C++ and Python style (#768) 3ebe4d6 unverified
AsukaMinato commited on
readme : add logo fece054 unverified
main : escape quotes in csv output (#815) 69030fd unverified
Laytan Laats commited on
stream : flush upon finishing inference (#811) 70c8984 unverified
Taras Glek commited on
examples : add missing #include <cstdint> (#798) f19517c unverified
Philipp Zabel commited on
main : update escape_double_quotes() function (#776) 3165de3 unverified
Tauseef Mohiuddin commited on
release : v1.3.0 016ac02 unverified
whisper : pad audio instead of spectrogram (#579) 8f647a2 unverified
whisper : restore decoder temperature fallbacks e02ade6 unverified
ggml, ci : fix build on whisper.android (ARM_NEON) + add CI (#764) dedf05b unverified
whisper : slightly faster Log Mel computation + n-1 FFT threads (#568) 542cfc1 unverified
readme : fix link e079132 unverified
readme : add usage instructions for Core ML 59d106a unverified
whisper : add Core ML support (#566) 1fd4bde unverified
whisper : do not launch log_mel threads when n_thread is 1 (#763) 4b562fc unverified
Maximiliano Levi commited on
whisper : fix the bug related to word splitting errors in the "tokenize" function. (#760) 0393a04 unverified
AfryMask AfryMask commited on
readme : add SwiftWhisper to listed bindings (#755) 9a0a719 unverified
Aaron Taylor commited on