whisper.cpp
whisper.cpp copied to clipboard
ggerganov
Port of OpenAI's Whisper model in C/C++
this PR is for multi purpose: (1) try to fix issue https://github.com/ggerganov/ggml/issues/795 (2) borrow some advantages from PyTorch(the user could specify whether a GGML OP(such as mulmat) is accelerated by...
Through CMake I managed to build main.exe and project for MS VS 2022, attempts to build project for Stream were not successful. Please help me either with setting CMakeLists.txt or...
Whisper.cpp fail to load model if it contains Hebrew characters in the path, happens in Rust bindings as well. ```console $ main.exe -m ggml-medium.bin -f single_speaker.wav $ echo %errorlevel% //...
No matter what stereo mp3 I convert with ffmpeg to wave --diarize did not work. Does anyone have a working sample mp3/wave file? I used following command: `./main -di -m...
I think Core ML is setup correct: Start whisper.cpp with: ` ./main --language de -t 10 -m models/ggml-medium.bin -f` ``` whisper_init_state: loading Core ML model from 'models/ggml-medium-encoder.mlmodelc' whisper_init_state: first run...
I have the latest commit at time of writing (8f253ef3af1c62c04316ba4afa7145fc4d701a8c), and am trying to use cmake to compile it instead of make, because I'm trying to debug an issue with...
Platform: `ubuntu 22.04` CPU: `amd ryzen-5 4500u` ```console $ sudo apt install -y libclblast-dev ocl-icd-opencl-dev mesa-opencl-icd $ git clone https://github.com/ggerganov/whisper.cpp $ cd whisper.cpp $ cmake -B build . -DWHISPER_CLBLAST=ON $...
Since Whisper is already so awesome I now want to push it a bit harder and simultaneously record input and output of a headset to different audio channels to generate...
- macOS Sonoma 14.4.1 - medium.en or medium 1.5.5  1.5.4  --- 1.5.5 Parameter Information  1.5.5 output information 
Reporting against a7508684 with ggml-large-v3-q5_0.bin. If the file to decode is very short (e.g. < 1s, single recorded word), the GGML version will consistently fail to output anything at all:...
