@sign-speak/react-sdk
Version:
Unlock Sign Language Recognition, Avatar, and Speech Recognition.
165 lines (164 loc) • 8.85 kB
JavaScript
;
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
var __generator = (this && this.__generator) || function (thisArg, body) {
var _ = { label: 0, sent: function() { if (t[0] & 1) throw t[1]; return t[1]; }, trys: [], ops: [] }, f, y, t, g;
return g = { next: verb(0), "throw": verb(1), "return": verb(2) }, typeof Symbol === "function" && (g[Symbol.iterator] = function() { return this; }), g;
function verb(n) { return function (v) { return step([n, v]); }; }
function step(op) {
if (f) throw new TypeError("Generator is already executing.");
while (g && (g = 0, op[0] && (_ = 0)), _) try {
if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
if (y = 0, t) op = [op[0] & 2, t.value];
switch (op[0]) {
case 0: case 1: t = op; break;
case 4: _.label++; return { value: op[1], done: false };
case 5: _.label++; y = op[1]; op = [0]; continue;
case 7: op = _.ops.pop(); _.trys.pop(); continue;
default:
if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) { _ = 0; continue; }
if (op[0] === 3 && (!t || (op[1] > t[0] && op[1] < t[3]))) { _.label = op[1]; break; }
if (op[0] === 6 && _.label < t[1]) { _.label = t[1]; t = op; break; }
if (t && _.label < t[2]) { _.label = t[2]; _.ops.push(op); break; }
if (t[2]) _.ops.pop();
_.trys.pop(); continue;
}
op = body.call(thisArg, _);
} catch (e) { op = [6, e]; y = 0; } finally { f = t = 0; }
if (op[0] & 5) throw op[1]; return { value: op[0] ? op[1] : void 0, done: true };
}
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.useSpeechRecognition = void 0;
var react_1 = require("react");
var rest_1 = require("../network/rest");
function useSpeechRecognition(config) {
var _this = this;
var _a = (0, react_1.useState)(), prediction = _a[0], setPrediction = _a[1];
var _b = (0, react_1.useState)(false), loading = _b[0], setLoading = _b[1];
var _c = (0, react_1.useState)(null), error = _c[0], setError = _c[1];
var _d = (0, react_1.useState)(false), recording = _d[0], setRecording = _d[1];
var configRef = (0, react_1.useRef)(config !== null && config !== void 0 ? config : {});
var streamRef = (0, react_1.useRef)(null);
var recorderRef = (0, react_1.useRef)(null);
(0, react_1.useEffect)(function () {
configRef.current = config !== null && config !== void 0 ? config : {};
}, [config]);
// Initializes the audio stream using getUserMedia. Optionally uses a specific device.
function initStream() {
var _a;
return __awaiter(this, void 0, void 0, function () {
var constraints, stream, err_1;
return __generator(this, function (_b) {
switch (_b.label) {
case 0:
if (streamRef.current)
return [2 /*return*/, streamRef.current];
_b.label = 1;
case 1:
_b.trys.push([1, 3, , 4]);
constraints = {
audio: ((_a = configRef.current) === null || _a === void 0 ? void 0 : _a.deviceId)
? { deviceId: { exact: configRef.current.deviceId } }
: true,
video: false,
};
return [4 /*yield*/, navigator.mediaDevices.getUserMedia(constraints)];
case 2:
stream = _b.sent();
streamRef.current = stream;
return [2 /*return*/, stream];
case 3:
err_1 = _b.sent();
setError(err_1);
throw err_1;
case 4: return [2 /*return*/];
}
});
});
}
// Start capturing audio and set up the recorder.
var startRecognition = function () { return __awaiter(_this, void 0, void 0, function () {
var stream, recorder, err_2;
var _this = this;
return __generator(this, function (_a) {
switch (_a.label) {
case 0:
_a.trys.push([0, 2, , 3]);
return [4 /*yield*/, initStream()];
case 1:
stream = _a.sent();
recorder = new MediaRecorder(stream);
recorderRef.current = recorder;
setRecording(true);
recorder.start();
recorder.ondataavailable = function (e) {
var blob = new Blob([e.data], { type: "audio/mp3" });
var reader = new FileReader();
reader.readAsDataURL(blob);
reader.onloadend = function () { return __awaiter(_this, void 0, void 0, function () {
var base64Audio, result, err_3;
var _a, _b, _c, _d;
return __generator(this, function (_e) {
switch (_e.label) {
case 0:
_e.trys.push([0, 2, 3, 4]);
setLoading(true);
base64Audio = reader.result.split(",")[1];
return [4 /*yield*/, (0, rest_1.recognizeSpeech)(base64Audio, {
model: (_b = (_a = configRef.current) === null || _a === void 0 ? void 0 : _a.model) !== null && _b !== void 0 ? _b : undefined,
language: (_d = (_c = configRef.current) === null || _c === void 0 ? void 0 : _c.language) !== null && _d !== void 0 ? _d : undefined
})];
case 1:
result = _e.sent();
setPrediction(result);
return [3 /*break*/, 4];
case 2:
err_3 = _e.sent();
setError(err_3);
return [3 /*break*/, 4];
case 3:
setLoading(false);
return [7 /*endfinally*/];
case 4: return [2 /*return*/];
}
});
}); };
};
recorder.onstop = function () {
setRecording(false);
};
return [3 /*break*/, 3];
case 2:
err_2 = _a.sent();
return [3 /*break*/, 3];
case 3: return [2 /*return*/];
}
});
}); };
// Stops the recording and cleans up the audio stream.
var stopRecognition = function () {
if (recorderRef.current && recorderRef.current.state === "recording") {
recorderRef.current.stop();
}
if (streamRef.current) {
streamRef.current.getTracks().forEach(function (track) { return track.stop(); });
streamRef.current = null;
}
};
(0, react_1.useEffect)(function () {
return function () {
// Cleanup on unmount.
stopRecognition();
};
}, []);
return { startRecognition: startRecognition, stopRecognition: stopRecognition, prediction: prediction, loading: loading, error: error, recording: recording };
}
exports.useSpeechRecognition = useSpeechRecognition;