MCPcopy Create free account
hub / github.com/FunAudioLLM/ThinkSound / sample

Function sample

ThinkSound/inference/sampling.py:48–86  ·  view source on GitHub ↗

Draws samples from a model given starting noise. v-diffusion

(model, x, steps, eta, **extra_args)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 5

predict_stepFunction · 0.90
predict_stepFunction · 0.90
predict_stepMethod · 0.85
on_train_batch_endMethod · 0.85
decodeMethod · 0.85

Calls 1

get_alphas_sigmasFunction · 0.85

Tested by

no test coverage detected