node-diarization/dist/src/recognition.js

Transcription and diarization using Whisper and Pyannote with NodeJS

"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    var desc = Object.getOwnPropertyDescriptor(m, k);
    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
      desc = { enumerable: true, get: function() { return m[k]; } };
    }
    Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
    Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
    o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
    var ownKeys = function(o) {
        ownKeys = Object.getOwnPropertyNames || function (o) {
            var ar = [];
            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
            return ar;
        };
        return ownKeys(o);
    };
    return function (mod) {
        if (mod && mod.__esModule) return mod;
        var result = {};
        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
        __setModuleDefault(result, mod);
        return result;
    };
})();
Object.defineProperty(exports, "__esModule", { value: true });
exports.parseSegmentsChunks = void 0;
const shell_1 = __importStar(require("./shell"));
const utils_1 = require("./utils");
const constants_1 = require("./constants");
const segmentRegex = /\{"id":\d+.*?"temperature":\d+\.\d+}/g;
const recognition = async (filePath, options, eventEmitter) => {
    const shellResult = await (0, shell_1.default)((0, shell_1.formatCommandString)('recognition', filePath, options), options, eventEmitter);
    // python script print segment, so we need to regex it
    // recognition shell result
    const segments = shellResult.data.match(segmentRegex);
    // split segments and main info
    const rSRSplit = shellResult.data.split(constants_1.RECOGNITION_PYDATA_DELIMITER);
    // add segments in main info
    if (rSRSplit[0]) {
        shellResult.data = rSRSplit[1].replace(/"recognition":\[]/, `"recognition":[${segments ? segments.join(',') : ''}]`);
    }
    return (0, utils_1.parseShellResult)(shellResult);
};
const parseSegmentsChunks = (textChunk) => {
    const segments = [];
    textChunk = textChunk.replace(segmentRegex, (segment) => {
        try {
            segments.push(JSON.parse(segment));
        }
        catch (e) {
        }
        return '';
    });
    return {
        textChunk,
        segments,
    };
};
exports.parseSegmentsChunks = parseSegmentsChunks;
exports.default = recognition;