constexpr size_t m_frameSizeMP3 = 18000; // more than one icy-metaint constexpr size_t m_frameSizeAAC = 18000; // more than one icy-metaint constexpr size_t m_frameSizeFLAC = UINT16_MAX; // max ogg ...
The entire high-level implementation of the model is contained in whisper.h and whisper.cpp. The rest of the code is part of the ggml machine learning library. Having such a lightweight implementation ...