vvolhejn

// For context, see: https://kyutai.org/next/tts
// and https://github.com/kyutai-labs/delayed-streams-modeling/issues/111

import { useEffect, useState, useRef, useCallback } from "react";
import useWebSocket, { ReadyState } from "react-use-websocket";
import { encode, decode, decodeAsync } from "@msgpack/msgpack";
import ttsVoices from "@/assets/tts_voices.json";

const SAMPLE_RATE = 24000;

vvolhejn

"""
The function `torch_conv_layer_to_affine` takes a `torch.nn.Conv2d` layer `conv`
and produces an equivalent `torch.nn.Linear` layer `fc`.

Specifically, this means that the following holds for `x` of a valid shape:
    torch.flatten(conv(x)) == fc(torch.flatten(x))

Or equivalently:
    conv(x) == fc(torch.flatten(x)).reshape(conv(x).shape)

vvolhejn

A/B testing, accuracy, action, activation function, active learning, AdaGrad, agent, agglomerative clustering, AR, area under the PR curve, area under the ROC curve, artificial general intelligence, artificial intelligence, attribute, AUC (Area under the ROC Curve), augmented reality, automation bias, average precision, backpropagation, bag of words, baseline, batch, batch normalization, batch size, Bayesian neural network, Bellman equation, bias (ethics/fairness), bias (math), bigram, binary classification, binning, boosting, bounding box, broadcasting, bucketing, calibration layer, candidate generation, candidate sampling, categorical data, centroid, centroid-based clustering, checkpoint, class, classification model, classification threshold, class-imbalanced dataset, clipping, Cloud TPU, clustering, co-adaptation, collaborative filtering, confirmation bias, confusion matrix, continuous feature, convenience sampling, convergence, convex function, convex optimization, convex set, convolution, convolutional f

vvolhejn

#include <iostream>
#include <vector>

using namespace std;

int main() {
    int n, k;
    cin >> n >> k;
    vector<int> a(n);
    for (int i = 0; i < n; i++) {

vvolhejn

#include <iostream>
#include <vector>

using namespace std;

int main() {
    int n, k;
    cin >> n >> k;
    vector<int> a(n);
    for (int i = 0; i < n; i++) {

vvolhejn

#include <iostream>
#include <vector>

using namespace std;

int main() {
    int n, k;
    cin >> n >> k;
    vector<int> a(n);
    for (int i = 0; i < n; i++) {

vvolhejn

Ktfjfa, Wsjxjwqgt, Ejbtfpwt, Wsjxjwqgt, Gqxqgft Xjxwqg, Btekqgwt, Gqxqgft Xjxwqg, Klxj Zsijhqga

Pgthqbeowqgt, Pkjnzqgpwl ftystxj, Ft Wfjxlnj, Iqhtfjnwt xtzstyt, Ft Wfjxlnj, Tsilpqgq ftklphj, Cjstpwqgq ftklphj

Gehtgpwt, Ueqslfn, Ftsqyfj hsjyt, Phtsqklphpwt

Pjilejqgt, Hztwosqgt, Bstpfa kqph, Gjhlxfl ftklphj

Ftystxj Zqelpqgjnl, Bstxpwa zsty, Gaplzsty, Qeptfpwt, Ftystxj Zqelpqgjnl

vvolhejn

Handle                   Language       Usage in last 50 submissions
--------------------------------------------------------------------
tourist                  GNU C++11      50
moejy0viiiiiv            GNU C++14      49
W4yneb0t                 GNU C++11      50
Petr                     Java 8         49
TakanashiRikka           GNU C++11      50
LHiC                     GNU C++11      50
izrak                    GNU C++14      48
anta                     GNU C++14      50