Hugging Face's logo

Spaces:
teralomaniac
/
sillytavern
Build error

App Files Community
sillytavern
File size: 4,159 Bytes 
70023bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
 
import { getApiUrl, doExtrasFetch, modules } from "../../extensions.js";
export { StreamingSttProvider }

const DEBUG_PREFIX = "<Speech Recognition module (streaming)> "

class StreamingSttProvider {
    //########//
    // Config //
    //########//

    settings

    defaultSettings = {
        triggerWordsText: "",
        triggerWords : [],
        triggerWordsEnabled : false,
        debug : false,
    }

    get settingsHtml() {
        let html = '\
        <div id="speech_recognition_streaming_trigger_words_div">\
        <span>Trigger words</span>\
        <textarea id="speech_recognition_streaming_trigger_words" class="text_pole textarea_compact" type="text" rows="4" placeholder="Enter comma separated words that triggers new message, example:\nhey, hey aqua, record, listen"></textarea>\
        <label class="checkbox_label" for="speech_recognition_streaming_trigger_words_enabled">\
            <input type="checkbox" id="speech_recognition_streaming_trigger_words_enabled" name="speech_recognition_trigger_words_enabled">\
            <small>Enable trigger words</small>\
        </label>\
        <label class="checkbox_label" for="speech_recognition_streaming_debug">\
            <input type="checkbox" id="speech_recognition_streaming_debug" name="speech_recognition_streaming_debug">\
            <small>Enable debug pop ups</small>\
        </label>\
        </div>\
        '
        return html
    }

    onSettingsChange() {
        this.settings.triggerWordsText = $('#speech_recognition_streaming_trigger_words').val();
        let array = $('#speech_recognition_streaming_trigger_words').val().split(",");
        array = array.map(element => {return element.trim().toLowerCase();});
        array = array.filter((str) => str !== '');
        this.settings.triggerWords = array;
        this.settings.triggerWordsEnabled = $("#speech_recognition_streaming_trigger_words_enabled").is(':checked');
        this.settings.debug = $("#speech_recognition_streaming_debug").is(':checked');
        console.debug(DEBUG_PREFIX+" Updated settings: ", this.settings);
        this.loadSettings(this.settings);
    }

    loadSettings(settings) {
        // Populate Provider UI given input settings
        if (Object.keys(settings).length == 0) {
            console.debug(DEBUG_PREFIX+"Using default Whisper STT extension settings")
        }

        // Only accept keys defined in defaultSettings
        this.settings = this.defaultSettings

        for (const key in settings){
            if (key in this.settings){
                this.settings[key] = settings[key]
            } else {
                throw `Invalid setting passed to STT extension: ${key}`
            }
        }

        $("#speech_recognition_streaming_trigger_words").val(this.settings.triggerWordsText);
        $("#speech_recognition_streaming_trigger_words_enabled").prop('checked',this.settings.triggerWordsEnabled);
        $("#speech_recognition_streaming_debug").prop('checked',this.settings.debug);

        console.debug(DEBUG_PREFIX+"streaming STT settings loaded")
    }

    async getUserMessage() {
        // Return if module is not loaded
        if (!modules.includes('streaming-stt')) {
            console.debug(DEBUG_PREFIX+"Module streaming-stt must be activated in Sillytavern Extras for streaming user voice.")
            return "";
        }

        const url = new URL(getApiUrl());
        url.pathname = '/api/speech-recognition/streaming/record-and-transcript';

        const apiResult = await doExtrasFetch(url, {
            method: 'POST',
            headers: {
                'Content-Type': 'application/json',
                'Bypass-Tunnel-Reminder': 'bypass',
            },
            body: JSON.stringify({ text: "" }),
        });

        if (!apiResult.ok) {
            toastr.error(apiResult.statusText, DEBUG_PREFIX+'STT Generation Failed  (streaming)', { timeOut: 10000, extendedTimeOut: 20000, preventDuplicates: true });
            throw new Error(`HTTP ${apiResult.status}: ${await apiResult.text()}`);
        }

        const data = await apiResult.json();
        return data.transcript;
    }

}