Q
C
R
T
SS
CC
H
sherpa-onnx
C
Cbeta
AA
HInferenceUpstreamError: must have required property 'prompt', must NOT have more than 6144 characters, must match exactly one schema in oneOf
DD
T
G
UGGGG
J
I
FIJ
K"InferenceUpstreamError: ERROR 3010: Invalid or incomplete input for the model: failed to decode JSON: Request is too large"
KS
STDD
D
R
@cf/microsoft/resnet-50 and @cf/runwayml/stable-diffusion-v1-5-img2img, and believe that the same would hold for any model that accepts a large input. I used the following to test and measure:{ audio: jsArray } to { image: jsArray } and calling resnet-50 would throw the same error. [123,78,30,255,0,...]. Unless there's a limit somewhere, then at some point something has to give. In this case, there seems to be a limit of just below 10 million bytes.
CKI
[<number>,<number>,<number>] (by a significant amount) but would need to be supported internally by Workers AI which I don't believe it is currentlyR@cf/microsoft/resnet-50, the actual inference can be a fraction of the total latency, where the rest is mainly due to juggling input data. I've done some testing on this.
R
), so I've turned my attention to wall time instead.F@cf/microsoft/resnet-50@cf/microsoft/resnet-50@cf/runwayml/stable-diffusion-v1-5-img2img{ audio: jsArray }{ image: jsArray }[123,78,30,255,0,...][<number>,<number>,<number>]const srcURL = "https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav";
const res = await fetch(srcURL);
const blob = await res.arrayBuffer();
const jsArray = [...new Uint8Array(blob)];
const input = { audio: jsArray };
console.log("Blob size: " + (jsArray.length / (2 << 19)).toFixed(1) + " MB");
console.log("Input array size: " + (jsArray.length / (2 << 17)).toFixed(1) + " MB");
// ai.run() stringifies input array before calling internal fetch:
// const inpBody = JSON.stringify({ inputs: input });
// console.log("JSON size: " + (inpBody.length / (2 << 19)).toFixed(1) + " MB");
const response = await ai.run("@cf/openai/whisper", input);