File size: 6,176 Bytes
519a20c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
import { saveTtsProviderSettings } from './index.js';

export { GptSovitsV2Provider };

class GptSovitsV2Provider {
    //########//
    // Config //
    //########//

    settings;
    ready = false;
    voices = [];
    separator = '. ';
    audioElement = document.createElement('audio');

    /**
     * Perform any text processing before passing to TTS engine.
     * @param {string} text Input text
     * @returns {string} Processed text
     */
    processText(text) {
        return text;
    }

    audioFormats = ['wav', 'ogg', 'silk', 'mp3', 'flac'];

    languageLabels = {
        'Auto': 'auto',
    };

    langKey2LangCode = {
        'zh': 'zh-CN',
        'en': 'en-US',
        'ja': 'ja-JP',
        'ko': 'ko-KR',
    };


    defaultSettings = {
        provider_endpoint: 'http://localhost:9880',
        format: 'wav',
        lang: 'auto',
        streaming: false,
        text_lang: 'zh',
        prompt_lang: 'zh',

    };

    get settingsHtml() {
        let html = `

        <label for="tts_endpoint">Provider Endpoint:</label>
        <input id="tts_endpoint" type="text" class="text_pole" maxlength="250" height="300" value="${this.defaultSettings.provider_endpoint}"/>
        <span>Use <a target="_blank" href="https://github.com/v3ucn/GPT-SoVITS-V2">GPT-SoVITS-V2</a>(Unofficial).</span><br/>
        <label for="text_lang">Text Lang(Inference text language):</label>
        <input id="text_lang" type="text" class="text_pole" maxlength="250" height="300" value="${this.defaultSettings.text_lang}"/>
        <label for="text_lang">Prompt Lang(Reference audio text language):</label>
        <input id="prompt_lang" type="text" class="text_pole" maxlength="250" height="300" value="${this.defaultSettings.prompt_lang}"/>
        <br/>

        `;

        return html;
    }

    onSettingsChange() {
        // Used when provider settings are updated from UI
        this.settings.provider_endpoint = $('#tts_endpoint').val();
        this.settings.text_lang = $('#text_lang').val();
        this.settings.prompt_lang = $('#prompt_lang').val();


        saveTtsProviderSettings();
        this.changeTTSSettings();
    }

    async loadSettings(settings) {
        // Pupulate Provider UI given input settings
        if (Object.keys(settings).length == 0) {
            console.info('Using default TTS Provider 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 {
                console.debug(`Ignoring non-user-configurable setting: ${key}`);
            }
        }

        // Set initial values from the settings
        $('#tts_endpoint').val(this.settings.provider_endpoint);
        $('#text_lang').val(this.settings.text_lang);
        $('#prompt_lang').val(this.settings.prompt_lang);


        await this.checkReady();

        console.info('ITS: Settings loaded');
    }

    // Perform a simple readiness check by trying to fetch voiceIds
    async checkReady() {
        await Promise.allSettled([this.fetchTtsVoiceObjects(), this.changeTTSSettings()]);
    }

    async onRefreshClick() {
        return;
    }

    //#################//
    //  TTS Interfaces //
    //#################//

    async getVoice(voiceName) {



        if (this.voices.length == 0) {
            this.voices = await this.fetchTtsVoiceObjects();
        }



        const match = this.voices.filter(
            v => v.name == voiceName,
        )[0];
        console.log(match);
        if (!match) {
            throw `TTS Voice name ${voiceName} not found`;
        }
        return match;
    }



    async generateTts(text, voiceId) {
        const response = await this.fetchTtsGeneration(text, voiceId);
        return response;
    }

    //###########//
    // API CALLS //
    //###########//
    async fetchTtsVoiceObjects() {
        const response = await fetch(`${this.settings.provider_endpoint}/speakers`);
        console.info(response);

        if (!response.ok) {
            throw new Error(`HTTP ${response.status}: ${await response.json()}`);
        }
        const responseJson = await response.json();


        this.voices = responseJson;

        return responseJson;
    }

    // Each time a parameter is changed, we change the configuration
    async changeTTSSettings() {
    }

    /**
     * Fetch TTS generation from the API.
     * @param {string} inputText Text to generate TTS for
     * @param {string} voiceId Voice ID to use (model_type&speaker_id))
     * @returns {Promise<Response|string>} Fetch response
     */




    async fetchTtsGeneration(inputText, voiceId, lang = null, forceNoStreaming = false) {
        console.info(`Generating new TTS for voice_id ${voiceId}`);

        function replaceSpeaker(text) {
            return text.replace(/\[.*?\]/gu, '');
        }

        let prompt_text = replaceSpeaker(voiceId);

        const params = {
            text: inputText,
            prompt_text: prompt_text,
            ref_audio_path: './ε‚θ€ƒιŸ³ι’‘/' + voiceId + '.wav',
            text_lang: this.settings.text_lang,
            prompt_lang: this.settings.prompt_lang,
            text_split_method: 'cut5',
            batch_size: 1,
            media_type: 'ogg',
            streaming_mode: 'true',
        };


        const url = `${this.settings.provider_endpoint}/`;

        const response = await fetch(
            url,
            {
                method: 'POST',
                headers: {
                    'Content-Type': 'application/json',
                },
                body: JSON.stringify(params), // Convert parameter objects to JSON strings
            },
        );
        if (!response.ok) {
            toastr.error(response.statusText, 'TTS Generation Failed');
            throw new Error(`HTTP ${response.status}: ${await response.text()}`);
        }
        return response;
    }



    // Interface not used
    async fetchTtsFromHistory(history_item_id) {
        return Promise.resolve(history_item_id);
    }
}