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

Function predict_step

predict.py:18–58  ·  view source on GitHub ↗
(diffusion, batch, diffusion_objective, device='cuda:0')

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

mainFunction · 0.70

Calls 4

sampleFunction · 0.90
sample_discrete_eulerFunction · 0.90
decodeMethod · 0.45

Tested by

no test coverage detected