Delete telegram bot and web version

Dockerfile

@@ -1,9 +0,0 @@
-FROM python:3.7
-COPY ./webapp /app
-WORKDIR /app
-RUN apt-get update
-RUN apt-get install -y ffmpeg
-RUN wget https://github.com/robinhad/voice-recognition-ua/releases/download/v0.4/uk.tflite
-# RUN wget https://github.com/robinhad/voice-recognition-ua/releases/download/v0.4/kenlm.scorer
-RUN pip install -r requirements.txt
-CMD uwsgi app.ini --http 0.0.0.0:$PORT

heroku.yml

@@ -1,3 +0,0 @@
-build:
-    docker:
-      web: Dockerfile

webapp/.dockerignore

@@ -1,7 +0,0 @@
-__pycache__/
-.venv/
-.env
-.git
-LICENSE
-README.md
-.github/

webapp/app.ini

@@ -1,8 +0,0 @@
-[uwsgi]
-wsgi-file = main.py
-callable = app
-http = :5000
-processes = 1
-master = true
-vacuum = true
-die-on-term = true

webapp/client.py

@@ -1,43 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import, division, print_function
-
-import numpy as np
-import sys
-import wave
-
-from deepspeech import Model, version
-from timeit import default_timer as timer
-
-
-def client(audio_file, lang="uk"):
-    model_load_start = timer()
-    # sphinx-doc: python_ref_model_start
-    model = "./uk.tflite"
-
-    ds = Model(model)
-    # ds.enableExternalScorer("kenlm.scorer")
-    # sphinx-doc: python_ref_model_stop
-    model_load_end = timer() - model_load_start
-    print('Loaded model in {:.3}s.'.format(model_load_end), file=sys.stderr)
-
-    desired_sample_rate = ds.sampleRate()
-
-    fin = wave.open(audio_file, 'rb')
-    fs_orig = fin.getframerate()
-    audio = np.frombuffer(fin.readframes(fin.getnframes()), np.int16)
-
-    audio_length = fin.getnframes() * (1/fs_orig)
-    fin.close()
-
-    print('Running inference.', file=sys.stderr)
-    inference_start = timer()
-    # sphinx-doc: python_ref_inference_start
-
-    result = ds.stt(audio)
-    print(result)
-    # sphinx-doc: python_ref_inference_stop
-    inference_end = timer() - inference_start
-    print('Inference took %0.3fs for %0.3fs audio file.' %
-          (inference_end, audio_length), file=sys.stderr)
-    return result

webapp/main.py

@@ -1,96 +0,0 @@
-from flask import Flask, render_template, request
-from io import BytesIO
-from client import client
-import telebot
-import logging
-import os
-import warnings
-from client import client
-from io import BytesIO
-import pydub
-
-warnings.simplefilter('ignore')
-TOKEN = os.environ['TOKEN']
-
-if not TOKEN:
-    print('You must set the TOKEN environment variable')
-    exit(1)
-
-START_MSG = '''Вітання!
-Цей бот створений для тестування перекладу українських аудіозаписів в текст.
-Група для обговорення: https://t.me/speech_recognition_uk'''
-
-FIRST_STEP = '''Використовувати бота просто: надішліть аудіоповідомлення і чекайте відповіді'''
-
-
-bot = telebot.TeleBot(TOKEN, parse_mode=None, threaded=False)
-app = Flask(__name__,)
-
-
-@app.route('/')
-def index():
-    bot.remove_webhook()
-    bot.set_webhook(
-        url='https://voice-recognition-ua.herokuapp.com/' + TOKEN)
-    return render_template('hello.html')
-
-
-@app.route('/recognize', methods=["POST"])
-def recognize():
-    file = request.files['file']
-    lang = request.form["lang"]
-    audio = BytesIO()
-    file.save(audio)
-    audio.seek(0)
-    result = client(audio, lang)
-    return result
-
-
-@app.route('/' + TOKEN, methods=['POST'])
-def getMessage():
-    bot.process_new_updates(
-        [telebot.types.Update.de_json(request.stream.read().decode("utf-8"))])
-    return "!", 200
-
-
-@bot.message_handler(commands=['start', 'help'])
-def send_welcome(message):
-    bot.reply_to(message, START_MSG)
-    bot.reply_to(message, FIRST_STEP)
-
-
-@bot.message_handler(content_types=['voice'])
-def process_voice_message(message):
-    # download the recording
-    file_info = bot.get_file(message.voice.file_id)
-    downloaded_file = bot.download_file(file_info.file_path)
-    # create in-memory representation of files
-    source_audio = BytesIO()
-    source_audio.write(downloaded_file)
-    source_audio.seek(0)
-    output_audio = BytesIO()
-    ogg_file = pydub.AudioSegment.from_ogg(
-        source_audio)
-
-    # convert ogg to wav
-    ogg_file.set_frame_rate(16000).set_channels(
-        1).export(output_audio, "wav", codec="pcm_s16le")
-    output_audio.seek(0)
-
-    # do the recognition
-    # get the recognized text
-    try:
-        text = client(output_audio)
-        # no results
-        if not text:
-            bot.reply_to(message, 'Я не зміг розпізнати 😢')
-        else:
-            # send the recognized text
-            bot.reply_to(message, text)
-    except Exception as e:
-        logging.log(logging.ERROR, str(e))
-        bot.reply_to(message, 'Трапилась помилка 😢')
-
-
-if __name__ == '__main__':
-    app.run(host='0.0.0.0')

webapp/requirements.txt

@@ -1,6 +0,0 @@
-Flask==1.1.2
-deepspeech-tflite==0.9.3
-numpy==1.17.0
-uwsgi==2.0.19.1
-pytelegrambotapi==3.7.6
-pydub==0.24.1

webapp/static/main.js

@@ -1,78 +0,0 @@
-// part of script inspired by https://github.com/addpipe/simple-recorderjs-demo
-var gumStream; 						//stream from getUserMedia()
-var rec; 							//Recorder.js object
-var input; 							//MediaStreamAudioSourceNode we'll be recording
-
-// shim for AudioContext when it's not avb. 
-var AudioContext = window.AudioContext || window.webkitAudioContext;
-var audioContext; //audio context to help us record
-const resultNode = document.getElementById('result');
-const actionButton = document.getElementById('action');
-const langSelector = document.getElementById('lang');
-
-function resultProcess(data) {
-    resultNode.textContent = `Довжина тексту: ${data.length} \n
-        Текст: ${data}
-    `;
-    actionButton.textContent = "Почати запис (3 сек)";
-    actionButton.disabled = false;
-}
-
-function exportWAV(blob) {
-    actionButton.textContent = "Обробляється..."
-    var data = new FormData()
-    data.append('file', blob);
-    data.append("lang", langSelector.value);
-    fetch(`./recognize`, { method: "POST", body: data })
-        .then(response => response.text())
-        .then(resultProcess);
-}
-function record() {
-
-    var constraints = { audio: true, video: false }
-    navigator.mediaDevices.getUserMedia(constraints).then(function (stream) {
-        actionButton.textContent = "Запис...";
-        resultNode.textContent = "";
-        actionButton.disabled = true;
-        /*
-            create an audio context after getUserMedia is called
-            sampleRate might change after getUserMedia is called, like it does on macOS when recording through AirPods
-            the sampleRate defaults to the one set in your OS for your playback device
-        */
-        audioContext = new AudioContext();
-
-        /*  assign to gumStream for later use  */
-        gumStream = stream;
-
-        /* use the stream */
-        input = audioContext.createMediaStreamSource(stream);
-
-        /* 
-            Create the Recorder object and configure to record mono sound (1 channel)
-            Recording 2 channels  will double the file size
-        */
-        rec = new Recorder(input, { numChannels: 1 })
-
-        //start the recording process
-        rec.record()
-        sleep(3000).then(stop);
-    })
-}
-
-
-function stop() {
-    rec.stop();
-
-    //stop microphone access
-    gumStream.getAudioTracks()[0].stop();
-
-    //create the wav blob and pass it on to createDownloadLink
-    rec.exportWAV(exportWAV);
-}
-
-
-const sleep = time => new Promise(resolve => setTimeout(resolve, time));
-
-async function handleAction() {
-    record();
-}

webapp/static/recorder.js

@@ -1,395 +0,0 @@
-//code taken from https://github.com/mattdiamond/Recorderjs/blob/master/src/recorder.js
-(function (f) { if (typeof exports === "object" && typeof module !== "undefined") { module.exports = f() } else if (typeof define === "function" && define.amd) { define([], f) } else { var g; if (typeof window !== "undefined") { g = window } else if (typeof global !== "undefined") { g = global } else if (typeof self !== "undefined") { g = self } else { g = this } g.Recorder = f() } })(function () {
-    var define, module, exports; return (function e(t, n, r) { function s(o, u) { if (!n[o]) { if (!t[o]) { var a = typeof require == "function" && require; if (!u && a) return a(o, !0); if (i) return i(o, !0); var f = new Error("Cannot find module '" + o + "'"); throw f.code = "MODULE_NOT_FOUND", f } var l = n[o] = { exports: {} }; t[o][0].call(l.exports, function (e) { var n = t[o][1][e]; return s(n ? n : e) }, l, l.exports, e, t, n, r) } return n[o].exports } var i = typeof require == "function" && require; for (var o = 0; o < r.length; o++)s(r[o]); return s })({
-        1: [function (require, module, exports) {
-            "use strict";
-
-            module.exports = require("./recorder").Recorder;
-
-        }, { "./recorder": 2 }], 2: [function (require, module, exports) {
-            'use strict';
-
-            var _createClass = (function () {
-                function defineProperties(target, props) {
-                    for (var i = 0; i < props.length; i++) {
-                        var descriptor = props[i]; descriptor.enumerable = descriptor.enumerable || false; descriptor.configurable = true; if ("value" in descriptor) descriptor.writable = true; Object.defineProperty(target, descriptor.key, descriptor);
-                    }
-                } return function (Constructor, protoProps, staticProps) {
-                    if (protoProps) defineProperties(Constructor.prototype, protoProps); if (staticProps) defineProperties(Constructor, staticProps); return Constructor;
-                };
-            })();
-
-            Object.defineProperty(exports, "__esModule", {
-                value: true
-            });
-            exports.Recorder = undefined;
-
-            var _inlineWorker = require('inline-worker');
-
-            var _inlineWorker2 = _interopRequireDefault(_inlineWorker);
-
-            function _interopRequireDefault(obj) {
-                return obj && obj.__esModule ? obj : { default: obj };
-            }
-
-            function _classCallCheck(instance, Constructor) {
-                if (!(instance instanceof Constructor)) {
-                    throw new TypeError("Cannot call a class as a function");
-                }
-            }
-
-            var Recorder = exports.Recorder = (function () {
-                function Recorder(source, cfg) {
-                    var _this = this;
-
-                    _classCallCheck(this, Recorder);
-
-                    this.config = {
-                        bufferLen: 4096,
-                        numChannels: 2,
-                        mimeType: 'audio/wav'
-                    };
-                    this.recording = false;
-                    this.callbacks = {
-                        getBuffer: [],
-                        exportWAV: []
-                    };
-
-                    Object.assign(this.config, cfg);
-                    this.context = source.context;
-                    this.node = (this.context.createScriptProcessor || this.context.createJavaScriptNode).call(this.context, this.config.bufferLen, this.config.numChannels, this.config.numChannels);
-
-                    this.node.onaudioprocess = function (e) {
-                        if (!_this.recording) return;
-
-                        var buffer = [];
-                        for (var channel = 0; channel < _this.config.numChannels; channel++) {
-                            buffer.push(e.inputBuffer.getChannelData(channel));
-                        }
-                        _this.worker.postMessage({
-                            command: 'record',
-                            buffer: buffer
-                        });
-                    };
-
-                    source.connect(this.node);
-                    this.node.connect(this.context.destination); //this should not be necessary
-
-                    var self = {};
-                    this.worker = new _inlineWorker2.default(function () {
-                        var recLength = 0,
-                            recBuffers = [],
-                            sampleRate = undefined,
-                            numChannels = undefined;
-
-                        self.onmessage = function (e) {
-                            switch (e.data.command) {
-                                case 'init':
-                                    init(e.data.config);
-                                    break;
-                                case 'record':
-                                    record(e.data.buffer);
-                                    break;
-                                case 'exportWAV':
-                                    exportWAV(e.data.type);
-                                    break;
-                                case 'getBuffer':
-                                    getBuffer();
-                                    break;
-                                case 'clear':
-                                    clear();
-                                    break;
-                            }
-                        };
-
-                        function init(config) {
-                            sampleRate = config.sampleRate;
-                            numChannels = config.numChannels;
-                            initBuffers();
-                        }
-
-                        function record(inputBuffer) {
-                            for (var channel = 0; channel < numChannels; channel++) {
-                                recBuffers[channel].push(inputBuffer[channel]);
-                            }
-                            recLength += inputBuffer[0].length;
-                        }
-
-                        function exportWAV(type) {
-                            var buffers = [];
-                            for (var channel = 0; channel < numChannels; channel++) {
-                                buffers.push(mergeBuffers(recBuffers[channel], recLength));
-                            }
-                            var interleaved = undefined;
-                            if (numChannels === 2) {
-                                interleaved = interleave(buffers[0], buffers[1]);
-                            } else {
-                                interleaved = buffers[0];
-                            }
-                            var downsampledBuffer = downsampleBuffer(interleaved, 16000);
-                            var dataview = encodeWAV(downsampledBuffer);
-                            var audioBlob = new Blob([dataview], { type: type });
-
-                            self.postMessage({ command: 'exportWAV', data: audioBlob });
-                        }
-
-                        function getBuffer() {
-                            var buffers = [];
-                            for (var channel = 0; channel < numChannels; channel++) {
-                                buffers.push(mergeBuffers(recBuffers[channel], recLength));
-                            }
-                            self.postMessage({ command: 'getBuffer', data: buffers });
-                        }
-
-                        function clear() {
-                            recLength = 0;
-                            recBuffers = [];
-                            initBuffers();
-                        }
-
-                        function initBuffers() {
-                            for (var channel = 0; channel < numChannels; channel++) {
-                                recBuffers[channel] = [];
-                            }
-                        }
-
-                        function mergeBuffers(recBuffers, recLength) {
-                            var result = new Float32Array(recLength);
-                            var offset = 0;
-                            for (var i = 0; i < recBuffers.length; i++) {
-                                result.set(recBuffers[i], offset);
-                                offset += recBuffers[i].length;
-                            }
-                            return result;
-                        }
-
-                        function downsampleBuffer(buffer, rate) {
-                            if (rate == sampleRate) {
-                                return buffer;
-                            }
-                            if (rate > sampleRate) {
-                                throw "downsampling rate show be smaller than original sample rate";
-                            }
-                            var sampleRateRatio = sampleRate / rate;
-                            var newLength = Math.round(buffer.length / sampleRateRatio);
-                            var result = new Float32Array(newLength);
-                            var offsetResult = 0;
-                            var offsetBuffer = 0;
-                            while (offsetResult < result.length) {
-                                var nextOffsetBuffer = Math.round((offsetResult + 1) * sampleRateRatio);
-                                // Use average value of skipped samples
-                                var accum = 0, count = 0;
-                                for (var i = offsetBuffer; i < nextOffsetBuffer && i < buffer.length; i++) {
-                                    accum += buffer[i];
-                                    count++;
-                                }
-                                result[offsetResult] = accum / count;
-                                // Or you can simply get rid of the skipped samples:
-                                // result[offsetResult] = buffer[nextOffsetBuffer];
-                                offsetResult++;
-                                offsetBuffer = nextOffsetBuffer;
-                            }
-                            return result;
-                        }
-
-                        function interleave(inputL, inputR) {
-                            var length = inputL.length + inputR.length;
-                            var result = new Float32Array(length);
-
-                            var index = 0,
-                                inputIndex = 0;
-
-                            while (index < length) {
-                                result[index++] = inputL[inputIndex];
-                                result[index++] = inputR[inputIndex];
-                                inputIndex++;
-                            }
-                            return result;
-                        }
-
-                        function floatTo16BitPCM(output, offset, input) {
-                            for (var i = 0; i < input.length; i++, offset += 2) {
-                                var s = Math.max(-1, Math.min(1, input[i]));
-                                output.setInt16(offset, s < 0 ? s * 0x8000 : s * 0x7FFF, true);
-                            }
-                        }
-
-                        function writeString(view, offset, string) {
-                            for (var i = 0; i < string.length; i++) {
-                                view.setUint8(offset + i, string.charCodeAt(i));
-                            }
-                        }
-
-                        function encodeWAV(samples) {
-                            var buffer = new ArrayBuffer(44 + samples.length * 2);
-                            var view = new DataView(buffer);
-
-                            /* RIFF identifier */
-                            writeString(view, 0, 'RIFF');
-                            /* RIFF chunk length */
-                            view.setUint32(4, 36 + samples.length * 2, true);
-                            /* RIFF type */
-                            writeString(view, 8, 'WAVE');
-                            /* format chunk identifier */
-                            writeString(view, 12, 'fmt ');
-                            /* format chunk length */
-                            view.setUint32(16, 16, true);
-                            /* sample format (raw) */
-                            view.setUint16(20, 1, true);
-                            /* channel count */
-                            view.setUint16(22, numChannels, true);
-                            /* sample rate */
-                            view.setUint32(24, 16000, true);
-                            /* byte rate (sample rate * block align) */
-                            view.setUint32(28, 16000 * 4, true);
-                            /* sample rate */
-                            //view.setUint32(24, sampleRate, true);
-                            /* byte rate (sample rate * block align) */
-                            //view.setUint32(28, sampleRate * 4, true);
-                            /* block align (channel count * bytes per sample) */
-                            view.setUint16(32, numChannels * 2, true);
-                            /* bits per sample */
-                            view.setUint16(34, 16, true);
-                            /* data chunk identifier */
-                            writeString(view, 36, 'data');
-                            /* data chunk length */
-                            view.setUint32(40, samples.length * 2, true);
-
-                            floatTo16BitPCM(view, 44, samples);
-
-                            return view;
-                        }
-                    }, self);
-
-                    this.worker.postMessage({
-                        command: 'init',
-                        config: {
-                            sampleRate: this.context.sampleRate,
-                            numChannels: this.config.numChannels
-                        }
-                    });
-
-                    this.worker.onmessage = function (e) {
-                        var cb = _this.callbacks[e.data.command].pop();
-                        if (typeof cb == 'function') {
-                            cb(e.data.data);
-                        }
-                    };
-                }
-
-                _createClass(Recorder, [{
-                    key: 'record',
-                    value: function record() {
-                        this.recording = true;
-                    }
-                }, {
-                    key: 'stop',
-                    value: function stop() {
-                        this.recording = false;
-                    }
-                }, {
-                    key: 'clear',
-                    value: function clear() {
-                        this.worker.postMessage({ command: 'clear' });
-                    }
-                }, {
-                    key: 'getBuffer',
-                    value: function getBuffer(cb) {
-                        cb = cb || this.config.callback;
-                        if (!cb) throw new Error('Callback not set');
-
-                        this.callbacks.getBuffer.push(cb);
-
-                        this.worker.postMessage({ command: 'getBuffer' });
-                    }
-                }, {
-                    key: 'exportWAV',
-                    value: function exportWAV(cb, mimeType) {
-                        mimeType = mimeType || this.config.mimeType;
-                        cb = cb || this.config.callback;
-                        if (!cb) throw new Error('Callback not set');
-
-                        this.callbacks.exportWAV.push(cb);
-
-                        this.worker.postMessage({
-                            command: 'exportWAV',
-                            type: mimeType
-                        });
-                    }
-                }], [{
-                    key: 'forceDownload',
-                    value: function forceDownload(blob, filename) {
-                        var url = (window.URL || window.webkitURL).createObjectURL(blob);
-                        var link = window.document.createElement('a');
-                        link.href = url;
-                        link.download = filename || 'output.wav';
-                        var click = document.createEvent("Event");
-                        click.initEvent("click", true, true);
-                        link.dispatchEvent(click);
-                    }
-                }]);
-
-                return Recorder;
-            })();
-
-            exports.default = Recorder;
-
-        }, { "inline-worker": 3 }], 3: [function (require, module, exports) {
-            "use strict";
-
-            module.exports = require("./inline-worker");
-        }, { "./inline-worker": 4 }], 4: [function (require, module, exports) {
-            (function (global) {
-                "use strict";
-
-                var _createClass = (function () { function defineProperties(target, props) { for (var key in props) { var prop = props[key]; prop.configurable = true; if (prop.value) prop.writable = true; } Object.defineProperties(target, props); } return function (Constructor, protoProps, staticProps) { if (protoProps) defineProperties(Constructor.prototype, protoProps); if (staticProps) defineProperties(Constructor, staticProps); return Constructor; }; })();
-
-                var _classCallCheck = function (instance, Constructor) { if (!(instance instanceof Constructor)) { throw new TypeError("Cannot call a class as a function"); } };
-
-                var WORKER_ENABLED = !!(global === global.window && global.URL && global.Blob && global.Worker);
-
-                var InlineWorker = (function () {
-                    function InlineWorker(func, self) {
-                        var _this = this;
-
-                        _classCallCheck(this, InlineWorker);
-
-                        if (WORKER_ENABLED) {
-                            var functionBody = func.toString().trim().match(/^function\s*\w*\s*\([\w\s,]*\)\s*{([\w\W]*?)}$/)[1];
-                            var url = global.URL.createObjectURL(new global.Blob([functionBody], { type: "text/javascript" }));
-
-                            return new global.Worker(url);
-                        }
-
-                        this.self = self;
-                        this.self.postMessage = function (data) {
-                            setTimeout(function () {
-                                _this.onmessage({ data: data });
-                            }, 0);
-                        };
-
-                        setTimeout(function () {
-                            func.call(self);
-                        }, 0);
-                    }
-
-                    _createClass(InlineWorker, {
-                        postMessage: {
-                            value: function postMessage(data) {
-                                var _this = this;
-
-                                setTimeout(function () {
-                                    _this.self.onmessage({ data: data });
-                                }, 0);
-                            }
-                        }
-                    });
-
-                    return InlineWorker;
-                })();
-
-                module.exports = InlineWorker;
-            }).call(this, typeof global !== "undefined" ? global : typeof self !== "undefined" ? self : typeof window !== "undefined" ? window : {})
-        }, {}]
-    }, {}, [1])(1)
-});

webapp/templates/hello.html

@@ -1,47 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-
-<head>
-    <meta charset="UTF-8">
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>Розпізнавання української мови</title>
-    <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/css/bootstrap.min.css"
-        integrity="sha384-ggOyR0iXCbMQv3Xipma34MD+dH/1fQ784/j6cY/iJTQUOhcWr7x9JvoRxT2MZw1T" crossorigin="anonymous">
-</head>
-
-<body>
-    <div class="container">
-        <div class="col-12 col-md-8 col-sm-12 col-xl-6 mx-auto text-center">
-            <h1>Демо розпізнавання української мови</h1>
-            <p>Говоріть 3 секунди після натискання на кнопку, тоді отримаєте результат</p>
-            <div class="row no-gutters">
-                <div class="col-1 col-sm-3">&nbsp;</div>
-                <div class="col-6">
-                    <button class="btn btn-primary" id="action" onclick="handleAction()">Почати запис (3 сек)</button>
-                </div>
-                <div class="col-5 col-sm-3">
-                    <select id="lang" class="browser-default custom-select" style="width: 100%">
-                        <option selected value="uk">Українська</option>
-                    </select>
-                </div>
-            </div>
-            <div id="result"></div>
-            <br>
-            <a href="https://commonvoice.mozilla.org/uk" target="_blank" class="btn btn-success" id="action">Долучитись
-                до створення відкритого
-                набору<br> записів української мови</a>
-            <br>
-            <div style="margin-top: 10px" class="alert alert-warning" role="alert">
-                Дисклеймер: через малу кількість даних для навчання нейромережі
-                результат може бути неточний:
-                <hr style="border-top-color:black">
-                сів метелик на травичку -> сі вметелик на требичко <br>
-                better late than never -> better waits and never
-            </div>
-        </div>
-    </div>
-    <script src="/static/recorder.js"></script>
-    <script src="/static/main.js"></script>
-</body>
-
-</html>