Spaces:
Running
Running
Commit History
refactoring : more readable code 5ef0168 unverified
correct model name display on running samples 10f411a
wasm : refactor wasm example + reuse fetch mechanism 3520198 unverified
talk.wasm : update video link + some minor fixes 33a4590 unverified
Update README.md 75f9881 unverified
Update README.md 668c7a5 unverified
talk.wasm : move to https://whisper.ggerganov.com/talk bee1ba7 unverified
models : add instructions for using HF fine-tuned models bd9b418 unverified
whisper : improve printfs bfa259c unverified
main : fix dangling pointer when using stdin for input (#65) 2daf96b unverified
main, stream : remove --verbose flag (#178) 8f1a93e unverified
talk.wasm : add audio pre-processing + bump memory 679d38e unverified
talk.wasm : refactoring + update README.md ff21a60 unverified
models : add usage comments to the HF convert script (#157) 8528ec5 unverified
models : fix HF fine-tuned model conversion script (#157) 6c811ac unverified
ggml : fix the fix 8b90727 unverified
ggml : fix cross-compile Linux -> Window with mingw (#168) 29fe0ee unverified
Revert "update README.md" 6b53c3a unverified
update README.md 96a13a8
katsu560 commited on
ggml: change inline ggml_fp16_to_fp32, ggml_fp16_t ggml_fp32_to_fp16 b2f844a
katsu560 commited on
add gprof option d44f972
katsu560 commited on
fix AVX,AVX2,FMA,F16C detection on Linux and add flags for OpenBLAS 7dc7c48
katsu560 commited on
add AVX support 00ac035
katsu560 commited on
Build with OpenBLAS and SDL2 on windows 71bf396
Tamotsu Takahashi commited on
models : minor changes to the HF convert script (#157) f500082 unverified
models : add "convert-h5-to-ggml.py" script (#157) 3568438 unverified
minor : updates few prints + fix buttons in whisper.wasm 7c7a4d7 unverified
Update README.md 87227d4 unverified
Update README.md 0f83fd2 unverified
Find libopenblas.dll.a on windows 6f7863e
Tamotsu Takahashi commited on
unicode : fix character replacement (thanks to @tamo) be06a9b unverified
close #109 : add fetching of the model over HTTP (whisper.wasm) 04da8a6 unverified
talk.wasm : final touches 722327a unverified
talk.wasm : polishing + adding many AI personalities b38c009 unverified
stream : "-kc" now enables context keeping from previous segment (#90) 28726dd unverified
Prompt previous tokens for streaming (#163) 8ad3dbf unverified
talk.wasm : update README.md 5cb7243 unverified
talk.wasm : GPT-2 meets Whisper in WebAssembly (#155) 411c667 unverified
Update README.md 59192b4 unverified
ggml : fix Windows build 42bbdcd
ci : add Windows build 48d2c3e
stream : add "max_tokens" cli arg 57a7bac
stream : add "audio_ctx" parameter 6adc1fe
stream : add "max_tokens" parameter e48ba5c
stream : add "single_segment" option a265bfa
stream : partial encoder experiments a2015c0
fix: free ggml_context (close #149) (#150) 06b8aa3 unverified
models : simplify the conversion script 1ffa4c8 unverified
Update download-ggml-model.sh 23d667f
Dody Suria Wijaya commited on