{ "audio": { "sample_rate": 22050, "quality": "medium" }, "espeak": { "voice": "en-gb-x-rp" }, "inference": { "noise_scale": 0.333, "length_scale": 1.4, "noise_w": 0.333 }, "phoneme_type": "espeak", "phoneme_map": {}, "phoneme_id_map": { "_": [ 0 ], "^": [ 1 ], "$": [ 2 ], " ": [ 3 ], "!": [ 4 ], "'": [ 5 ], "(": [ 6 ], ")": [ 7 ], ",": [ 8 ], "-": [ 9 ], ".": [ 10 ], ":": [ 11 ], ";": [ 12 ], "?": [ 13 ], "a": [ 14 ], "b": [ 15 ], "c": [ 16 ], "d": [ 17 ], "e": [ 18 ], "f": [ 19 ], "h": [ 20 ], "i": [ 21 ], "j": [ 22 ], "k": [ 23 ], "l": [ 24 ], "m": [ 25 ], "n": [ 26 ], "o": [ 27 ], "p": [ 28 ], "q": [ 29 ], "r": [ 30 ], "s": [ 31 ], "t": [ 32 ], "u": [ 33 ], "v": [ 34 ], "w": [ 35 ], "x": [ 36 ], "y": [ 37 ], "z": [ 38 ], "æ": [ 39 ], "ç": [ 40 ], "ð": [ 41 ], "ø": [ 42 ], "ħ": [ 43 ], "ŋ": [ 44 ], "œ": [ 45 ], "ǀ": [ 46 ], "ǁ": [ 47 ], "ǂ": [ 48 ], "ǃ": [ 49 ], "ɐ": [ 50 ], "ɑ": [ 51 ], "ɒ": [ 52 ], "ɓ": [ 53 ], "ɔ": [ 54 ], "ɕ": [ 55 ], "ɖ": [ 56 ], "ɗ": [ 57 ], "ɘ": [ 58 ], "ə": [ 59 ], "ɚ": [ 60 ], "ɛ": [ 61 ], "ɜ": [ 62 ], "ɞ": [ 63 ], "ɟ": [ 64 ], "ɠ": [ 65 ], "ɡ": [ 66 ], "ɢ": [ 67 ], "ɣ": [ 68 ], "ɤ": [ 69 ], "ɥ": [ 70 ], "ɦ": [ 71 ], "ɧ": [ 72 ], "ɨ": [ 73 ], "ɪ": [ 74 ], "ɫ": [ 75 ], "ɬ": [ 76 ], "ɭ": [ 77 ], "ɮ": [ 78 ], "ɯ": [ 79 ], "ɰ": [ 80 ], "ɱ": [ 81 ], "ɲ": [ 82 ], "ɳ": [ 83 ], "ɴ": [ 84 ], "ɵ": [ 85 ], "ɶ": [ 86 ], "ɸ": [ 87 ], "ɹ": [ 88 ], "ɺ": [ 89 ], "ɻ": [ 90 ], "ɽ": [ 91 ], "ɾ": [ 92 ], "ʀ": [ 93 ], "ʁ": [ 94 ], "ʂ": [ 95 ], "ʃ": [ 96 ], "ʄ": [ 97 ], "ʈ": [ 98 ], "ʉ": [ 99 ], "ʊ": [ 100 ], "ʋ": [ 101 ], "ʌ": [ 102 ], "ʍ": [ 103 ], "ʎ": [ 104 ], "ʏ": [ 105 ], "ʐ": [ 106 ], "ʑ": [ 107 ], "ʒ": [ 108 ], "ʔ": [ 109 ], "ʕ": [ 110 ], "ʘ": [ 111 ], "ʙ": [ 112 ], "ʛ": [ 113 ], "ʜ": [ 114 ], "ʝ": [ 115 ], "ʟ": [ 116 ], "ʡ": [ 117 ], "ʢ": [ 118 ], "ʲ": [ 119 ], "ˈ": [ 120 ], "ˌ": [ 121 ], "ː": [ 122 ], "ˑ": [ 123 ], "˞": [ 124 ], "β": [ 125 ], "θ": [ 126 ], "χ": [ 127 ], "ᵻ": [ 128 ], "ⱱ": [ 129 ], "0": [ 130 ], "1": [ 131 ], "2": [ 132 ], "3": [ 133 ], "4": [ 134 ], "5": [ 135 ], "6": [ 136 ], "7": [ 137 ], "8": [ 138 ], "9": [ 139 ], "̧": [ 140 ], "̃": [ 141 ], "̪": [ 142 ], "̯": [ 143 ], "̩": [ 144 ], "ʰ": [ 145 ], "ˤ": [ 146 ], "ε": [ 147 ], "↓": [ 148 ], "#": [ 149 ], "\"": [ 150 ], "↑": [ 151 ], "̺": [ 152 ], "̻": [ 153 ] }, "num_symbols": 256, "num_speakers": 109, "speaker_id_map": { "p239": 0, "p236": 1, "p264": 2, "p250": 3, "p259": 4, "p247": 5, "p261": 6, "p263": 7, "p283": 8, "p286": 9, "p274": 10, "p276": 11, "p270": 12, "p281": 13, "p277": 14, "p231": 15, "p271": 16, "p238": 17, "p257": 18, "p273": 19, "p284": 20, "p329": 21, "p361": 22, "p287": 23, "p360": 24, "p374": 25, "p376": 26, "p310": 27, "p304": 28, "p334": 29, "p340": 30, "p323": 31, "p347": 32, "p330": 33, "p308": 34, "p314": 35, "p317": 36, "p339": 37, "p311": 38, "p294": 39, "p305": 40, "p266": 41, "p335": 42, "p318": 43, "p351": 44, "p333": 45, "p313": 46, "p316": 47, "p244": 48, "p307": 49, "p363": 50, "p336": 51, "p297": 52, "p312": 53, "p267": 54, "p275": 55, "p295": 56, "p258": 57, "p288": 58, "p301": 59, "p232": 60, "p292": 61, "p272": 62, "p280": 63, "p278": 64, "p341": 65, "p268": 66, "p298": 67, "p299": 68, "p279": 69, "p285": 70, "p326": 71, "p300": 72, "s5": 73, "p230": 74, "p345": 75, "p254": 76, "p269": 77, "p293": 78, "p252": 79, "p262": 80, "p243": 81, "p227": 82, "p343": 83, "p255": 84, "p229": 85, "p240": 86, "p248": 87, "p253": 88, "p233": 89, "p228": 90, "p282": 91, "p251": 92, "p246": 93, "p234": 94, "p226": 95, "p260": 96, "p245": 97, "p241": 98, "p303": 99, "p265": 100, "p306": 101, "p237": 102, "p249": 103, "p256": 104, "p302": 105, "p364": 106, "p225": 107, "p362": 108 }, "piper_version": "1.0.0", "language": { "code": "en_GB", "family": "en", "region": "GB", "name_native": "English", "name_english": "English", "country_english": "Great Britain" }, "dataset": "vctk" }