jonatasgrosman commited on
Commit
c626fd7
1 Parent(s): fa1b8ce

jonatasgrosman/exp_w2v2t_ja_unispeech-sat_s635

Browse files
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ja
4
+ license: apache-2.0
5
+ tags:
6
+ - automatic-speech-recognition
7
+ - ja
8
+ datasets:
9
+ - mozilla-foundation/common_voice_7_0
10
+ ---
11
+ # exp_w2v2t_ja_unispeech-sat_s635
12
+
13
+ Fine-tuned [microsoft/unispeech-sat-large](https://huggingface.co/microsoft/unispeech-sat-large) for speech recognition using the train split of [Common Voice 7.0 (ja)](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0).
14
+ When using this model, make sure that your speech input is sampled at 16kHz.
15
+
16
+ This model has been fine-tuned by the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) tool.
17
+
config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/unispeech-sat-large",
3
+ "activation_dropout": 0.05,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "UniSpeechSatForCTC"
7
+ ],
8
+ "attention_dropout": 0.05,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 768,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": false,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "sum",
42
+ "ctc_zero_infinity": false,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.05,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.05,
52
+ "hidden_act": "gelu",
53
+ "hidden_dropout": 0.05,
54
+ "hidden_size": 1024,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 4096,
57
+ "layer_norm_eps": 1e-05,
58
+ "layerdrop": 0.05,
59
+ "mask_feature_length": 10,
60
+ "mask_feature_min_masks": 0,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_masks": 2,
64
+ "mask_time_prob": 0.05,
65
+ "model_type": "unispeech-sat",
66
+ "num_attention_heads": 16,
67
+ "num_clusters": 504,
68
+ "num_codevector_groups": 2,
69
+ "num_codevectors_per_group": 320,
70
+ "num_conv_pos_embedding_groups": 16,
71
+ "num_conv_pos_embeddings": 128,
72
+ "num_feat_extract_layers": 7,
73
+ "num_hidden_layers": 24,
74
+ "num_negatives": 100,
75
+ "pad_token_id": 0,
76
+ "proj_codevector_dim": 768,
77
+ "tdnn_dilation": [
78
+ 1,
79
+ 2,
80
+ 3,
81
+ 1,
82
+ 1
83
+ ],
84
+ "tdnn_dim": [
85
+ 512,
86
+ 512,
87
+ 512,
88
+ 512,
89
+ 1500
90
+ ],
91
+ "tdnn_kernel": [
92
+ 5,
93
+ 3,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
99
+ "torch_dtype": "float32",
100
+ "transformers_version": "4.16.0.dev0",
101
+ "use_weighted_layer_sum": false,
102
+ "vocab_size": 2121,
103
+ "xvector_output_dim": 512
104
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73ea9792ca31bb821a54bf010de17a1d36784d9a44b425814854422aa114330
3
+ size 1270607039
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/tmp/tmpnoqeo38s", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
transcriptions_cv7_test.json ADDED
The diff for this file is too large to render. See raw diff
 
transcriptions_cv7_validation.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "'": 5, "-": 6, "a": 7, "b": 8, "c": 9, "d": 10, "e": 11, "f": 12, "g": 13, "h": 14, "i": 15, "j": 16, "k": 17, "l": 18, "m": 19, "n": 20, "o": 21, "p": 22, "q": 23, "r": 24, "s": 25, "t": 26, "u": 27, "v": 28, "w": 29, "x": 30, "y": 31, "z": 32, "々": 33, "あ": 34, "い": 35, "う": 36, "ぇ": 37, "え": 38, "お": 39, "か": 40, "が": 41, "き": 42, "ぎ": 43, "く": 44, "ぐ": 45, "け": 46, "げ": 47, "こ": 48, "ご": 49, "さ": 50, "ざ": 51, "し": 52, "じ": 53, "す": 54, "ず": 55, "せ": 56, "ぜ": 57, "そ": 58, "ぞ": 59, "た": 60, "だ": 61, "ち": 62, "っ": 63, "つ": 64, "づ": 65, "て": 66, "で": 67, "と": 68, "ど": 69, "な": 70, "に": 71, "ぬ": 72, "ね": 73, "の": 74, "は": 75, "ば": 76, "ぱ": 77, "ひ": 78, "び": 79, "ぴ": 80, "ふ": 81, "ぶ": 82, "ぷ": 83, "へ": 84, "べ": 85, "ぺ": 86, "ほ": 87, "ぼ": 88, "ぽ": 89, "ま": 90, "み": 91, "む": 92, "め": 93, "も": 94, "ゃ": 95, "や": 96, "ゅ": 97, "ゆ": 98, "ょ": 99, "よ": 100, "ら": 101, "り": 102, "る": 103, "れ": 104, "ろ": 105, "わ": 106, "を": 107, "ん": 108, "ァ": 109, "ア": 110, "ィ": 111, "イ": 112, "ゥ": 113, "ウ": 114, "ェ": 115, "エ": 116, "ォ": 117, "オ": 118, "カ": 119, "ガ": 120, "キ": 121, "ギ": 122, "ク": 123, "グ": 124, "ケ": 125, "ゲ": 126, "コ": 127, "ゴ": 128, "サ": 129, "ザ": 130, "シ": 131, "ジ": 132, "ス": 133, "ズ": 134, "セ": 135, "ゼ": 136, "ソ": 137, "ゾ": 138, "タ": 139, "ダ": 140, "チ": 141, "ッ": 142, "ツ": 143, "ヅ": 144, "テ": 145, "デ": 146, "ト": 147, "ド": 148, "ナ": 149, "ニ": 150, "ヌ": 151, "ネ": 152, "ノ": 153, "ハ": 154, "バ": 155, "パ": 156, "ヒ": 157, "ビ": 158, "ピ": 159, "フ": 160, "ブ": 161, "プ": 162, "ヘ": 163, "ベ": 164, "ペ": 165, "ホ": 166, "ボ": 167, "ポ": 168, "マ": 169, "ミ": 170, "ム": 171, "メ": 172, "モ": 173, "ャ": 174, "ヤ": 175, "ュ": 176, "ユ": 177, "ョ": 178, "ヨ": 179, "ラ": 180, "リ": 181, "ル": 182, "レ": 183, "ロ": 184, "ワ": 185, "ン": 186, "ヴ": 187, "ヶ": 188, "ー": 189, "一": 190, "丁": 191, "七": 192, "万": 193, "丈": 194, "三": 195, "上": 196, "下": 197, "不": 198, "与": 199, "世": 200, "丘": 201, "両": 202, "並": 203, "中": 204, "丸": 205, "丹": 206, "主": 207, "丼": 208, "久": 209, "乏": 210, "乗": 211, "乙": 212, "九": 213, "乞": 214, "乱": 215, "乳": 216, "乾": 217, "亀": 218, "了": 219, "予": 220, "争": 221, "事": 222, "二": 223, "互": 224, "五": 225, "井": 226, "亜": 227, "亡": 228, "交": 229, "京": 230, "人": 231, "今": 232, "介": 233, "仏": 234, "仕": 235, "他": 236, "付": 237, "代": 238, "令": 239, "以": 240, "仮": 241, "仰": 242, "仲": 243, "件": 244, "任": 245, "企": 246, "伏": 247, "伐": 248, "休": 249, "会": 250, "伝": 251, "伯": 252, "伴": 253, "伸": 254, "似": 255, "位": 256, "低": 257, "住": 258, "佐": 259, "体": 260, "何": 261, "余": 262, "作": 263, "併": 264, "使": 265, "例": 266, "供": 267, "依": 268, "価": 269, "侵": 270, "侶": 271, "便": 272, "係": 273, "促": 274, "俗": 275, "保": 276, "信": 277, "俣": 278, "修": 279, "俳": 280, "俺": 281, "倉": 282, "個": 283, "倍": 284, "倒": 285, "候": 286, "借": 287, "倣": 288, "値": 289, "倫": 290, "偉": 291, "偏": 292, "停": 293, "健": 294, "側": 295, "偶": 296, "偽": 297, "傑": 298, "備": 299, "催": 300, "債": 301, "傷": 302, "傾": 303, "僅": 304, "働": 305, "像": 306, "僕": 307, "僚": 308, "僧": 309, "儀": 310, "億": 311, "償": 312, "優": 313, "元": 314, "兄": 315, "充": 316, "兆": 317, "先": 318, "光": 319, "克": 320, "免": 321, "児": 322, "党": 323, "入": 324, "全": 325, "八": 326, "公": 327, "六": 328, "共": 329, "兵": 330, "其": 331, "具": 332, "典": 333, "兼": 334, "内": 335, "円": 336, "冊": 337, "再": 338, "冑": 339, "冒": 340, "冗": 341, "写": 342, "冠": 343, "冬": 344, "冶": 345, "冷": 346, "凍": 347, "凝": 348, "処": 349, "凶": 350, "出": 351, "刀": 352, "刃": 353, "分": 354, "切": 355, "刈": 356, "刊": 357, "刑": 358, "列": 359, "初": 360, "判": 361, "別": 362, "利": 363, "到": 364, "制": 365, "刷": 366, "券": 367, "刺": 368, "刻": 369, "剃": 370, "則": 371, "削": 372, "前": 373, "剣": 374, "剤": 375, "剥": 376, "副": 377, "剰": 378, "割": 379, "創": 380, "劇": 381, "力": 382, "功": 383, "加": 384, "劣": 385, "助": 386, "努": 387, "励": 388, "労": 389, "効": 390, "勃": 391, "勅": 392, "勇": 393, "勉": 394, "動": 395, "勘": 396, "務": 397, "勝": 398, "募": 399, "勢": 400, "勤": 401, "勧": 402, "勲": 403, "勾": 404, "包": 405, "化": 406, "北": 407, "匹": 408, "区": 409, "医": 410, "匿": 411, "十": 412, "千": 413, "午": 414, "半": 415, "卒": 416, "卓": 417, "協": 418, "南": 419, "単": 420, "博": 421, "占": 422, "印": 423, "危": 424, "即": 425, "却": 426, "卵": 427, "卿": 428, "厄": 429, "厚": 430, "原": 431, "厳": 432, "去": 433, "参": 434, "又": 435, "及": 436, "友": 437, "双": 438, "反": 439, "収": 440, "叔": 441, "取": 442, "受": 443, "叙": 444, "口": 445, "古": 446, "句": 447, "叩": 448, "只": 449, "叫": 450, "召": 451, "可": 452, "台": 453, "史": 454, "右": 455, "号": 456, "司": 457, "各": 458, "合": 459, "吉": 460, "吊": 461, "同": 462, "名": 463, "后": 464, "吐": 465, "向": 466, "君": 467, "吠": 468, "否": 469, "含": 470, "吸": 471, "吹": 472, "呂": 473, "呆": 474, "呈": 475, "告": 476, "周": 477, "味": 478, "呼": 479, "命": 480, "和": 481, "咲": 482, "品": 483, "員": 484, "哲": 485, "哺": 486, "唆": 487, "唇": 488, "唯": 489, "唱": 490, "商": 491, "問": 492, "啓": 493, "善": 494, "喉": 495, "喜": 496, "喧": 497, "喩": 498, "喪": 499, "喫": 500, "営": 501, "嗅": 502, "嘘": 503, "嘩": 504, "噂": 505, "噛": 506, "器": 507, "噴": 508, "囚": 509, "四": 510, "回": 511, "因": 512, "団": 513, "困": 514, "囲": 515, "図": 516, "固": 517, "国": 518, "圏": 519, "園": 520, "土": 521, "圧": 522, "在": 523, "地": 524, "坂": 525, "均": 526, "坊": 527, "垂": 528, "型": 529, "垣": 530, "埋": 531, "城": 532, "域": 533, "執": 534, "培": 535, "基": 536, "堀": 537, "堂": 538, "堆": 539, "堕": 540, "堤": 541, "堪": 542, "報": 543, "場": 544, "塀": 545, "塁": 546, "塊": 547, "塔": 548, "塗": 549, "塞": 550, "塩": 551, "填": 552, "塹": 553, "境": 554, "墓": 555, "増": 556, "壁": 557, "壇": 558, "壊": 559, "壌": 560, "壕": 561, "士": 562, "壮": 563, "声": 564, "売": 565, "変": 566, "夏": 567, "夕": 568, "外": 569, "多": 570, "夜": 571, "夢": 572, "大": 573, "天": 574, "太": 575, "夫": 576, "央": 577, "失": 578, "奇": 579, "奈": 580, "奉": 581, "奏": 582, "契": 583, "奔": 584, "奥": 585, "奨": 586, "奪": 587, "奮": 588, "女": 589, "奴": 590, "好": 591, "如": 592, "妊": 593, "妖": 594, "妙": 595, "妨": 596, "妹": 597, "妻": 598, "姉": 599, "始": 600, "姓": 601, "委": 602, "姦": 603, "姿": 604, "威": 605, "娘": 606, "娠": 607, "娯": 608, "娼": 609, "婚": 610, "婦": 611, "媒": 612, "媽": 613, "嫌": 614, "嬉": 615, "子": 616, "孔": 617, "字": 618, "存": 619, "季": 620, "孤": 621, "学": 622, "孫": 623, "孵": 624, "宅": 625, "宇": 626, "守": 627, "安": 628, "宋": 629, "完": 630, "宗": 631, "官": 632, "宙": 633, "定": 634, "宜": 635, "宝": 636, "実": 637, "客": 638, "宣": 639, "室": 640, "宮": 641, "害": 642, "家": 643, "容": 644, "宿": 645, "寄": 646, "密": 647, "富": 648, "寒": 649, "寝": 650, "察": 651, "寡": 652, "寧": 653, "審": 654, "寮": 655, "寸": 656, "寺": 657, "対": 658, "寿": 659, "封": 660, "専": 661, "射": 662, "将": 663, "尉": 664, "尊": 665, "尋": 666, "導": 667, "小": 668, "少": 669, "尖": 670, "尤": 671, "就": 672, "尺": 673, "尻": 674, "尾": 675, "尿": 676, "局": 677, "居": 678, "屈": 679, "届": 680, "屋": 681, "展": 682, "属": 683, "層": 684, "履": 685, "屯": 686, "山": 687, "岐": 688, "岩": 689, "岳": 690, "岸": 691, "島": 692, "崇": 693, "崔": 694, "崖": 695, "崩": 696, "嵐": 697, "川": 698, "州": 699, "巡": 700, "巣": 701, "工": 702, "左": 703, "巧": 704, "巨": 705, "差": 706, "己": 707, "巻": 708, "市": 709, "布": 710, "希": 711, "帝": 712, "帥": 713, "師": 714, "席": 715, "帯": 716, "帰": 717, "帳": 718, "常": 719, "帽": 720, "幅": 721, "幕": 722, "幣": 723, "干": 724, "平": 725, "年": 726, "幸": 727, "幹": 728, "幻": 729, "幼": 730, "幾": 731, "庁": 732, "広": 733, "床": 734, "序": 735, "底": 736, "店": 737, "府": 738, "度": 739, "座": 740, "庫": 741, "庭": 742, "庵": 743, "康": 744, "廃": 745, "廊": 746, "廟": 747, "延": 748, "廷": 749, "建": 750, "弁": 751, "式": 752, "弓": 753, "引": 754, "弟": 755, "弦": 756, "弧": 757, "弩": 758, "弱": 759, "張": 760, "強": 761, "弾": 762, "当": 763, "彗": 764, "彙": 765, "形": 766, "彩": 767, "彫": 768, "彰": 769, "影": 770, "役": 771, "彼": 772, "往": 773, "征": 774, "径": 775, "待": 776, "律": 777, "後": 778, "徐": 779, "徒": 780, "従": 781, "得": 782, "御": 783, "復": 784, "微": 785, "徳": 786, "徴": 787, "徹": 788, "心": 789, "必": 790, "忍": 791, "志": 792, "忘": 793, "忙": 794, "応": 795, "忠": 796, "快": 797, "念": 798, "怒": 799, "怖": 800, "思": 801, "怠": 802, "急": 803, "性": 804, "怪": 805, "恋": 806, "恐": 807, "恒": 808, "恨": 809, "恩": 810, "息": 811, "恰": 812, "恵": 813, "悠": 814, "患": 815, "悩": 816, "悪": 817, "悲": 818, "悶": 819, "情": 820, "惑": 821, "惜": 822, "惟": 823, "惨": 824, "想": 825, "惹": 826, "愉": 827, "意": 828, "愕": 829, "愛": 830, "感": 831, "慈": 832, "態": 833, "慌": 834, "慎": 835, "慢": 836, "慣": 837, "慮": 838, "憎": 839, "憧": 840, "憩": 841, "憲": 842, "憶": 843, "懇": 844, "懐": 845, "懸": 846, "成": 847, "我": 848, "戒": 849, "或": 850, "戦": 851, "戴": 852, "戸": 853, "戻": 854, "房": 855, "所": 856, "扇": 857, "扉": 858, "手": 859, "才": 860, "打": 861, "払": 862, "扮": 863, "扱": 864, "批": 865, "承": 866, "技": 867, "把": 868, "抑": 869, "投": 870, "抗": 871, "折": 872, "抜": 873, "択": 874, "披": 875, "抱": 876, "抵": 877, "押": 878, "抽": 879, "担": 880, "拍": 881, "拐": 882, "拒": 883, "拓": 884, "拘": 885, "招": 886, "拝": 887, "拠": 888, "拡": 889, "括": 890, "拭": 891, "拳": 892, "拶": 893, "拷": 894, "持": 895, "指": 896, "挑": 897, "挙": 898, "挨": 899, "挫": 900, "振": 901, "挿": 902, "捉": 903, "捕": 904, "捧": 905, "捨": 906, "掃": 907, "授": 908, "排": 909, "掘": 910, "掛": 911, "採": 912, "探": 913, "接": 914, "控": 915, "推": 916, "措": 917, "掲": 918, "揃": 919, "描": 920, "提": 921, "揚": 922, "換": 923, "握": 924, "揮": 925, "援": 926, "揺": 927, "損": 928, "搭": 929, "携": 930, "搾": 931, "摂": 932, "摘": 933, "摩": 934, "撃": 935, "撤": 936, "撮": 937, "撲": 938, "擁": 939, "操": 940, "擦": 941, "支": 942, "改": 943, "攻": 944, "放": 945, "政": 946, "故": 947, "救": 948, "敗": 949, "教": 950, "敢": 951, "散": 952, "敬": 953, "数": 954, "整": 955, "敵": 956, "敷": 957, "文": 958, "斉": 959, "斎": 960, "斑": 961, "料": 962, "斜": 963, "斧": 964, "断": 965, "斯": 966, "新": 967, "方": 968, "施": 969, "旅": 970, "旋": 971, "族": 972, "旗": 973, "既": 974, "日": 975, "旦": 976, "旧": 977, "旨": 978, "早": 979, "旬": 980, "昆": 981, "昇": 982, "昌": 983, "明": 984, "昏": 985, "易": 986, "昔": 987, "星": 988, "映": 989, "春": 990, "昨": 991, "是": 992, "昼": 993, "時": 994, "晩": 995, "普": 996, "景": 997, "晴": 998, "晶": 999, "暇": 1000, "暑": 1001, "暖": 1002, "暗": 1003, "暢": 1004, "暫": 1005, "暮": 1006, "暴": 1007, "曜": 1008, "曲": 1009, "曳": 1010, "更": 1011, "書": 1012, "替": 1013, "最": 1014, "月": 1015, "有": 1016, "服": 1017, "朗": 1018, "望": 1019, "朝": 1020, "期": 1021, "木": 1022, "未": 1023, "末": 1024, "本": 1025, "札": 1026, "机": 1027, "朽": 1028, "杉": 1029, "材": 1030, "村": 1031, "杖": 1032, "束": 1033, "条": 1034, "来": 1035, "東": 1036, "松": 1037, "板": 1038, "析": 1039, "枕": 1040, "林": 1041, "枚": 1042, "果": 1043, "枝": 1044, "枠": 1045, "枢": 1046, "枯": 1047, "架": 1048, "柄": 1049, "染": 1050, "柔": 1051, "柱": 1052, "柳": 1053, "柵": 1054, "査": 1055, "栄": 1056, "栓": 1057, "校": 1058, "株": 1059, "核": 1060, "根": 1061, "格": 1062, "栽": 1063, "案": 1064, "桎": 1065, "桜": 1066, "桟": 1067, "梅": 1068, "梏": 1069, "梨": 1070, "械": 1071, "棄": 1072, "棒": 1073, "棚": 1074, "棟": 1075, "森": 1076, "棲": 1077, "椅": 1078, "植": 1079, "椎": 1080, "検": 1081, "楕": 1082, "業": 1083, "極": 1084, "楼": 1085, "楽": 1086, "概": 1087, "構": 1088, "槍": 1089, "様": 1090, "槽": 1091, "標": 1092, "模": 1093, "権": 1094, "横": 1095, "樹": 1096, "橄": 1097, "橋": 1098, "橙": 1099, "機": 1100, "欄": 1101, "欖": 1102, "欠": 1103, "次": 1104, "欧": 1105, "欲": 1106, "欺": 1107, "歌": 1108, "歓": 1109, "止": 1110, "正": 1111, "武": 1112, "歩": 1113, "歯": 1114, "歳": 1115, "歴": 1116, "死": 1117, "殉": 1118, "殊": 1119, "残": 1120, "殖": 1121, "殴": 1122, "段": 1123, "殺": 1124, "殻": 1125, "殿": 1126, "毅": 1127, "母": 1128, "毎": 1129, "毒": 1130, "比": 1131, "毛": 1132, "氏": 1133, "民": 1134, "気": 1135, "水": 1136, "氷": 1137, "永": 1138, "汁": 1139, "求": 1140, "汎": 1141, "汚": 1142, "汝": 1143, "江": 1144, "池": 1145, "汰": 1146, "汲": 1147, "決": 1148, "沃": 1149, "沈": 1150, "没": 1151, "沢": 1152, "河": 1153, "沸": 1154, "油": 1155, "治": 1156, "沼": 1157, "沿": 1158, "況": 1159, "泉": 1160, "泊": 1161, "法": 1162, "泡": 1163, "波": 1164, "泣": 1165, "泥": 1166, "注": 1167, "泳": 1168, "洋": 1169, "洗": 1170, "洞": 1171, "活": 1172, "派": 1173, "流": 1174, "浄": 1175, "浅": 1176, "浪": 1177, "浮": 1178, "浴": 1179, "海": 1180, "浸": 1181, "消": 1182, "涙": 1183, "涯": 1184, "液": 1185, "涼": 1186, "淘": 1187, "淡": 1188, "深": 1189, "混": 1190, "添": 1191, "清": 1192, "済": 1193, "渉": 1194, "渋": 1195, "渓": 1196, "減": 1197, "渡": 1198, "渦": 1199, "温": 1200, "測": 1201, "港": 1202, "湖": 1203, "湯": 1204, "湾": 1205, "湿": 1206, "満": 1207, "源": 1208, "準": 1209, "溜": 1210, "溢": 1211, "溶": 1212, "滅": 1213, "滑": 1214, "滝": 1215, "滞": 1216, "滴": 1217, "漁": 1218, "漂": 1219, "漏": 1220, "漑": 1221, "演": 1222, "漕": 1223, "漠": 1224, "漢": 1225, "漫": 1226, "潜": 1227, "潤": 1228, "潮": 1229, "激": 1230, "濁": 1231, "濃": 1232, "濡": 1233, "瀕": 1234, "瀬": 1235, "灌": 1236, "火": 1237, "灯": 1238, "灰": 1239, "災": 1240, "炉": 1241, "炊": 1242, "炎": 1243, "炙": 1244, "炭": 1245, "点": 1246, "為": 1247, "烈": 1248, "焉": 1249, "無": 1250, "焦": 1251, "然": 1252, "焼": 1253, "煉": 1254, "煙": 1255, "照": 1256, "煮": 1257, "煽": 1258, "熊": 1259, "熟": 1260, "熱": 1261, "熾": 1262, "燃": 1263, "燈": 1264, "燕": 1265, "燥": 1266, "爆": 1267, "爪": 1268, "爬": 1269, "爵": 1270, "父": 1271, "爽": 1272, "片": 1273, "版": 1274, "牛": 1275, "牡": 1276, "牧": 1277, "物": 1278, "牲": 1279, "特": 1280, "犀": 1281, "犠": 1282, "犬": 1283, "犯": 1284, "状": 1285, "狂": 1286, "狙": 1287, "狩": 1288, "独": 1289, "狼": 1290, "猛": 1291, "猟": 1292, "猫": 1293, "献": 1294, "猿": 1295, "獄": 1296, "獣": 1297, "獲": 1298, "率": 1299, "玉": 1300, "王": 1301, "珍": 1302, "現": 1303, "球": 1304, "理": 1305, "璧": 1306, "環": 1307, "瓦": 1308, "瓶": 1309, "甘": 1310, "生": 1311, "産": 1312, "甥": 1313, "用": 1314, "田": 1315, "由": 1316, "甲": 1317, "申": 1318, "男": 1319, "町": 1320, "画": 1321, "界": 1322, "畑": 1323, "留": 1324, "畜": 1325, "略": 1326, "番": 1327, "異": 1328, "疎": 1329, "疑": 1330, "疫": 1331, "疲": 1332, "疽": 1333, "疾": 1334, "病": 1335, "症": 1336, "痕": 1337, "痛": 1338, "痩": 1339, "瘍": 1340, "療": 1341, "癌": 1342, "癒": 1343, "発": 1344, "登": 1345, "白": 1346, "百": 1347, "的": 1348, "皆": 1349, "皇": 1350, "皮": 1351, "盆": 1352, "益": 1353, "盗": 1354, "盛": 1355, "盟": 1356, "監": 1357, "盤": 1358, "目": 1359, "盲": 1360, "直": 1361, "相": 1362, "盾": 1363, "省": 1364, "眉": 1365, "看": 1366, "県": 1367, "真": 1368, "眠": 1369, "眺": 1370, "眼": 1371, "着": 1372, "睡": 1373, "督": 1374, "瞬": 1375, "瞭": 1376, "矛": 1377, "矢": 1378, "知": 1379, "短": 1380, "矯": 1381, "石": 1382, "砂": 1383, "研": 1384, "砕": 1385, "砦": 1386, "砲": 1387, "破": 1388, "硝": 1389, "硫": 1390, "硬": 1391, "碁": 1392, "碑": 1393, "確": 1394, "磁": 1395, "磨": 1396, "礎": 1397, "礫": 1398, "示": 1399, "礼": 1400, "社": 1401, "祈": 1402, "祖": 1403, "祝": 1404, "神": 1405, "祠": 1406, "祥": 1407, "票": 1408, "祭": 1409, "禁": 1410, "福": 1411, "秀": 1412, "私": 1413, "科": 1414, "秒": 1415, "秘": 1416, "秦": 1417, "秩": 1418, "称": 1419, "移": 1420, "稀": 1421, "程": 1422, "税": 1423, "種": 1424, "稼": 1425, "稿": 1426, "穀": 1427, "積": 1428, "穏": 1429, "穴": 1430, "究": 1431, "空": 1432, "突": 1433, "窒": 1434, "窓": 1435, "窟": 1436, "窮": 1437, "窯": 1438, "立": 1439, "竜": 1440, "章": 1441, "童": 1442, "端": 1443, "競": 1444, "竹": 1445, "笑": 1446, "笛": 1447, "符": 1448, "第": 1449, "筆": 1450, "筈": 1451, "等": 1452, "筋": 1453, "筒": 1454, "答": 1455, "策": 1456, "箋": 1457, "箔": 1458, "算": 1459, "管": 1460, "箱": 1461, "節": 1462, "範": 1463, "築": 1464, "篤": 1465, "簡": 1466, "籍": 1467, "米": 1468, "粉": 1469, "粋": 1470, "粒": 1471, "粗": 1472, "粘": 1473, "粧": 1474, "精": 1475, "糖": 1476, "糸": 1477, "系": 1478, "糾": 1479, "紀": 1480, "約": 1481, "紅": 1482, "紋": 1483, "納": 1484, "純": 1485, "紙": 1486, "級": 1487, "紛": 1488, "素": 1489, "索": 1490, "紫": 1491, "細": 1492, "紳": 1493, "紹": 1494, "終": 1495, "組": 1496, "絆": 1497, "経": 1498, "結": 1499, "絞": 1500, "絡": 1501, "給": 1502, "絨": 1503, "統": 1504, "絵": 1505, "絶": 1506, "継": 1507, "続": 1508, "綜": 1509, "維": 1510, "網": 1511, "綴": 1512, "綺": 1513, "綿": 1514, "緊": 1515, "総": 1516, "緑": 1517, "緒": 1518, "線": 1519, "締": 1520, "編": 1521, "緩": 1522, "練": 1523, "縁": 1524, "縛": 1525, "縞": 1526, "縦": 1527, "縫": 1528, "縮": 1529, "績": 1530, "繁": 1531, "繊": 1532, "繋": 1533, "織": 1534, "繞": 1535, "繫": 1536, "繰": 1537, "缶": 1538, "罠": 1539, "罪": 1540, "置": 1541, "罰": 1542, "署": 1543, "罹": 1544, "羅": 1545, "羊": 1546, "美": 1547, "群": 1548, "義": 1549, "羽": 1550, "翅": 1551, "翌": 1552, "習": 1553, "翻": 1554, "翼": 1555, "老": 1556, "考": 1557, "者": 1558, "而": 1559, "耐": 1560, "耕": 1561, "耗": 1562, "耳": 1563, "聖": 1564, "聞": 1565, "聴": 1566, "職": 1567, "肉": 1568, "肌": 1569, "肖": 1570, "肘": 1571, "肝": 1572, "股": 1573, "肢": 1574, "肥": 1575, "肩": 1576, "肪": 1577, "肯": 1578, "育": 1579, "肺": 1580, "胆": 1581, "背": 1582, "胎": 1583, "胞": 1584, "胱": 1585, "胴": 1586, "胸": 1587, "能": 1588, "脂": 1589, "脅": 1590, "脇": 1591, "脈": 1592, "脊": 1593, "脚": 1594, "脱": 1595, "脳": 1596, "腎": 1597, "腐": 1598, "腕": 1599, "腫": 1600, "腰": 1601, "腸": 1602, "腹": 1603, "腺": 1604, "膀": 1605, "膏": 1606, "膜": 1607, "膝": 1608, "膣": 1609, "膨": 1610, "膳": 1611, "膾": 1612, "膿": 1613, "臓": 1614, "臣": 1615, "臨": 1616, "自": 1617, "臭": 1618, "至": 1619, "致": 1620, "臼": 1621, "興": 1622, "舌": 1623, "舎": 1624, "舗": 1625, "舞": 1626, "舟": 1627, "航": 1628, "般": 1629, "舶": 1630, "船": 1631, "艦": 1632, "良": 1633, "色": 1634, "芝": 1635, "花": 1636, "芳": 1637, "芸": 1638, "芽": 1639, "苔": 1640, "苗": 1641, "若": 1642, "苦": 1643, "英": 1644, "茂": 1645, "茅": 1646, "茎": 1647, "茶": 1648, "草": 1649, "荊": 1650, "荒": 1651, "荷": 1652, "菌": 1653, "菓": 1654, "菜": 1655, "華": 1656, "萎": 1657, "落": 1658, "葉": 1659, "著": 1660, "葛": 1661, "董": 1662, "葦": 1663, "葬": 1664, "葺": 1665, "蒙": 1666, "蒸": 1667, "蒼": 1668, "蓄": 1669, "蓋": 1670, "蔓": 1671, "蔗": 1672, "蔦": 1673, "蔵": 1674, "薄": 1675, "薇": 1676, "薔": 1677, "薬": 1678, "藍": 1679, "藤": 1680, "蘇": 1681, "虎": 1682, "虐": 1683, "虚": 1684, "虜": 1685, "虫": 1686, "虹": 1687, "蛋": 1688, "蛙": 1689, "蛮": 1690, "蜂": 1691, "蜃": 1692, "蜜": 1693, "蝋": 1694, "蝶": 1695, "融": 1696, "蠣": 1697, "血": 1698, "衆": 1699, "行": 1700, "術": 1701, "街": 1702, "衛": 1703, "衝": 1704, "衡": 1705, "衣": 1706, "表": 1707, "衰": 1708, "袋": 1709, "被": 1710, "裁": 1711, "裂": 1712, "装": 1713, "裏": 1714, "裕": 1715, "補": 1716, "裸": 1717, "製": 1718, "裾": 1719, "複": 1720, "褐": 1721, "襲": 1722, "西": 1723, "要": 1724, "覆": 1725, "覇": 1726, "見": 1727, "規": 1728, "視": 1729, "覚": 1730, "覧": 1731, "親": 1732, "観": 1733, "角": 1734, "解": 1735, "触": 1736, "言": 1737, "訂": 1738, "計": 1739, "討": 1740, "訓": 1741, "託": 1742, "記": 1743, "訛": 1744, "訟": 1745, "訪": 1746, "設": 1747, "許": 1748, "訳": 1749, "訴": 1750, "診": 1751, "証": 1752, "詐": 1753, "評": 1754, "詞": 1755, "試": 1756, "詩": 1757, "詰": 1758, "話": 1759, "詳": 1760, "誇": 1761, "誉": 1762, "誌": 1763, "認": 1764, "誓": 1765, "誕": 1766, "誘": 1767, "語": 1768, "誠": 1769, "誤": 1770, "説": 1771, "読": 1772, "誰": 1773, "課": 1774, "調": 1775, "談": 1776, "請": 1777, "論": 1778, "諸": 1779, "謀": 1780, "謎": 1781, "謖": 1782, "講": 1783, "謝": 1784, "識": 1785, "警": 1786, "議": 1787, "譲": 1788, "護": 1789, "讃": 1790, "讐": 1791, "谷": 1792, "豆": 1793, "豊": 1794, "豚": 1795, "象": 1796, "豪": 1797, "貌": 1798, "貞": 1799, "負": 1800, "財": 1801, "貢": 1802, "貧": 1803, "貨": 1804, "販": 1805, "貪": 1806, "貫": 1807, "責": 1808, "貯": 1809, "貴": 1810, "買": 1811, "貸": 1812, "費": 1813, "貼": 1814, "貿": 1815, "賃": 1816, "資": 1817, "賛": 1818, "賞": 1819, "賢": 1820, "質": 1821, "賭": 1822, "購": 1823, "贅": 1824, "贈": 1825, "贖": 1826, "赤": 1827, "赦": 1828, "走": 1829, "起": 1830, "超": 1831, "越": 1832, "趣": 1833, "足": 1834, "距": 1835, "跡": 1836, "路": 1837, "跳": 1838, "践": 1839, "踊": 1840, "踏": 1841, "蹄": 1842, "蹴": 1843, "躁": 1844, "躍": 1845, "身": 1846, "車": 1847, "軋": 1848, "軌": 1849, "軍": 1850, "軟": 1851, "転": 1852, "軸": 1853, "軻": 1854, "軽": 1855, "較": 1856, "載": 1857, "輝": 1858, "輩": 1859, "輪": 1860, "輸": 1861, "轄": 1862, "辛": 1863, "辞": 1864, "辣": 1865, "辱": 1866, "農": 1867, "辺": 1868, "込": 1869, "迎": 1870, "近": 1871, "返": 1872, "迫": 1873, "述": 1874, "迷": 1875, "追": 1876, "退": 1877, "送": 1878, "逃": 1879, "逆": 1880, "透": 1881, "逐": 1882, "途": 1883, "這": 1884, "通": 1885, "速": 1886, "造": 1887, "連": 1888, "逮": 1889, "週": 1890, "進": 1891, "逸": 1892, "遂": 1893, "遅": 1894, "遇": 1895, "遊": 1896, "運": 1897, "遍": 1898, "過": 1899, "道": 1900, "達": 1901, "違": 1902, "遠": 1903, "遡": 1904, "遣": 1905, "遥": 1906, "適": 1907, "遭": 1908, "遮": 1909, "遷": 1910, "選": 1911, "遺": 1912, "遼": 1913, "避": 1914, "還": 1915, "邦": 1916, "邪": 1917, "郊": 1918, "郎": 1919, "郡": 1920, "部": 1921, "郵": 1922, "郷": 1923, "都": 1924, "酋": 1925, "配": 1926, "酒": 1927, "酔": 1928, "酢": 1929, "酵": 1930, "酷": 1931, "酸": 1932, "醇": 1933, "醍": 1934, "醐": 1935, "醒": 1936, "醜": 1937, "醸": 1938, "采": 1939, "釈": 1940, "里": 1941, "重": 1942, "野": 1943, "量": 1944, "金": 1945, "釣": 1946, "鉄": 1947, "鉱": 1948, "銀": 1949, "銃": 1950, "銅": 1951, "銘": 1952, "鋤": 1953, "鋭": 1954, "鋼": 1955, "錠": 1956, "錨": 1957, "錬": 1958, "録": 1959, "鍋": 1960, "鍛": 1961, "鎖": 1962, "鎮": 1963, "鏡": 1964, "鐘": 1965, "鑑": 1966, "長": 1967, "門": 1968, "閉": 1969, "開": 1970, "閑": 1971, "間": 1972, "関": 1973, "閣": 1974, "閥": 1975, "閲": 1976, "闇": 1977, "闘": 1978, "防": 1979, "附": 1980, "降": 1981, "限": 1982, "陛": 1983, "院": 1984, "陣": 1985, "除": 1986, "陥": 1987, "陰": 1988, "陳": 1989, "陵": 1990, "陶": 1991, "陸": 1992, "険": 1993, "陽": 1994, "隅": 1995, "隊": 1996, "階": 1997, "随": 1998, "隔": 1999, "隕": 2000, "際": 2001, "障": 2002, "隠": 2003, "隣": 2004, "隷": 2005, "雀": 2006, "雄": 2007, "雅": 2008, "集": 2009, "雇": 2010, "雌": 2011, "雑": 2012, "離": 2013, "難": 2014, "雨": 2015, "雪": 2016, "雰": 2017, "雲": 2018, "零": 2019, "雷": 2020, "電": 2021, "需": 2022, "震": 2023, "霊": 2024, "霧": 2025, "露": 2026, "青": 2027, "静": 2028, "非": 2029, "面": 2030, "革": 2031, "靴": 2032, "鞭": 2033, "韓": 2034, "音": 2035, "韻": 2036, "響": 2037, "頂": 2038, "頃": 2039, "項": 2040, "順": 2041, "須": 2042, "頑": 2043, "領": 2044, "頬": 2045, "頭": 2046, "頷": 2047, "頸": 2048, "頻": 2049, "頼": 2050, "顆": 2051, "題": 2052, "額": 2053, "顔": 2054, "顕": 2055, "願": 2056, "類": 2057, "顧": 2058, "風": 2059, "飛": 2060, "食": 2061, "飢": 2062, "飯": 2063, "飲": 2064, "飼": 2065, "飽": 2066, "飾": 2067, "養": 2068, "餐": 2069, "餓": 2070, "館": 2071, "饉": 2072, "首": 2073, "香": 2074, "馬": 2075, "馳": 2076, "駄": 2077, "駅": 2078, "駆": 2079, "駈": 2080, "駐": 2081, "騎": 2082, "騒": 2083, "験": 2084, "騰": 2085, "驚": 2086, "骨": 2087, "骸": 2088, "高": 2089, "髪": 2090, "髭": 2091, "鬱": 2092, "魂": 2093, "魅": 2094, "魔": 2095, "魚": 2096, "鮮": 2097, "鯛": 2098, "鰭": 2099, "鳥": 2100, "鳩": 2101, "鳴": 2102, "鴨": 2103, "鶏": 2104, "鶯": 2105, "鷹": 2106, "麗": 2107, "麦": 2108, "麺": 2109, "麻": 2110, "黄": 2111, "黒": 2112, "黙": 2113, "鼓": 2114, "鼻": 2115, "齢": 2116, "齧": 2117, "龍": 2118, "h": 2119, "j": 2120}