MCPcopy Create free account
hub / github.com/0xShug0/audio.cpp / audio_frames_per_latent

Function audio_frames_per_latent

src/models/ace_step/vae_decoder.cpp:554–566  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

552}
553
554int64_t audio_frames_per_latent(const AceStepVAEConfig & config) {
555 if (config.downsampling_ratios.empty()) {
556 throw std::runtime_error("ACE-Step VAE requires downsampling ratios");
557 }
558 int64_t factor = 1;
559 for (const int64_t ratio : config.downsampling_ratios) {
560 if (ratio <= 0) {
561 throw std::runtime_error("ACE-Step VAE downsampling ratio must be positive");
562 }
563 factor *= ratio;
564 }
565 return factor;
566}
567
568} // namespace vae_common
569

Callers 2

decodeMethod · 0.85
encodeMethod · 0.85

Calls 1

emptyMethod · 0.45

Tested by

no test coverage detected