Training in progress, step 700

config.json

@@ -0,0 +1,124 @@
+{
+  "vocab_size": 51865,
+  "num_mel_bins": 80,
+  "d_model": 1280,
+  "encoder_layers": 32,
+  "encoder_attention_heads": 20,
+  "decoder_layers": 6,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "encoder_ffn_dim": 5120,
+  "dropout": 0.0,
+  "attention_dropout": 0.0,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "init_std": 0.02,
+  "encoder_layerdrop": 0.0,
+  "decoder_layerdrop": 0.0,
+  "use_cache": true,
+  "num_hidden_layers": 32,
+  "scale_embedding": false,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "classifier_proj_size": 256,
+  "use_weighted_layer_sum": false,
+  "apply_spec_augment": false,
+  "mask_time_prob": 0.05,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_feature_prob": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "median_filter_width": 7,
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": true,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "architectures": null,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": 50256,
+  "pad_token_id": 50256,
+  "eos_token_id": 50256,
+  "sep_token_id": null,
+  "decoder_start_token_id": 50257,
+  "task_specific_params": null,
+  "problem_type": null,
+  "_name_or_path": "",
+  "transformers_version": "4.42.3",
+  "model_type": "syllable_whisper",
+  "encoder_type": "embedding",
+  "freeze_wav2vec": false,
+  "phoneme_vocab_size": 55,
+  "syllable_vocab_size": 1207,
+  "loss_lambda": 0.5,
+  "alignment_lambda": 0.5,
+  "phoneme_grouping_size": 3,
+  "phoneme_pad_token_id": 2,
+  "phoneme_bos_token_id": 1,
+  "phoneme_eos_token_id": 1,
+  "syllable_pad_token_id": 2,
+  "syllable_bos_token_id": 1,
+  "syllable_eos_token_id": 1,
+  "num_layer_stacks": 1,
+  "noise_std": 0.01,
+  "apply_noise_to_original": false,
+  "original_encoder_layers": 32,
+  "unfreeze_top_k_layers": 0,
+  "original_decoder_layers": 6,
+  "reduce_encoder_layers": false,
+  "reduce_decoder_layers": false,
+  "encoder_layers_to_keep": 32,
+  "decoder_layers_to_keep": 6,
+  "decoder_dropout_rate": 0.0,
+  "decoder_dropout_type": "standard",
+  "apply_dropout_to_stacked_only": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877fb1ff35869fdf6b24e1fe5888b1e985fda0539f91e5d236374ce020f3bc1f
+size 1312261992

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Jul22_12-22-38_whisper-finetune.asia-northeast3-a.c.sabina-404403.internal/events.out.tfevents.1753186963.whisper-finetune.asia-northeast3-a.c.sabina-404403.internal.1867.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a0be984b84a9ea61677fe20c44bea2e7e778899d241f13a70d5fb6b5312acb4
+size 6220

runs/Jul22_12-22-38_whisper-finetune.asia-northeast3-a.c.sabina-404403.internal/events.out.tfevents.1753188305.whisper-finetune.asia-northeast3-a.c.sabina-404403.internal.1867.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bccc95011186fc45b7202f82104ab1ccd8f9c1fe6a867ab6ab4678b482061b
+size 4433

runs/Jul22_12-22-38_whisper-finetune.asia-northeast3-a.c.sabina-404403.internal/events.out.tfevents.1753188305.whisper-finetune.asia-northeast3-a.c.sabina-404403.internal.1867.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06b6446d9ed405732321110ed0a650014a0901e4cc26375b17cccd0fa074365
+size 88

runs/Jul22_12-22-38_whisper-finetune.asia-northeast3-a.c.sabina-404403.internal/events.out.tfevents.1753188341.whisper-finetune.asia-northeast3-a.c.sabina-404403.internal.1867.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a84c31c6ec6cfeabf39cc2b2a073549259862a0bafb5be12da99269813c41fd
+size 4433

runs/Jul22_12-22-38_whisper-finetune.asia-northeast3-a.c.sabina-404403.internal/events.out.tfevents.1753188341.whisper-finetune.asia-northeast3-a.c.sabina-404403.internal.1867.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9cf9bfc9234bd1d851187d38aaeca067f474965ad2433ef8b12ef6e7a15637
+size 88

runs/Jul22_12-22-38_whisper-finetune.asia-northeast3-a.c.sabina-404403.internal/events.out.tfevents.1753188360.whisper-finetune.asia-northeast3-a.c.sabina-404403.internal.1867.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6af360ed925406e7e88f10849d12481f9e5461bc3356057af02c7eaca934bf2
+size 4433

tokenizers/p_vocab.json

@@ -0,0 +1,57 @@
+{
+  "0": "<s>",
+  "1": "</s>",
+  "2": "<pad>",
+  "3": "<unk>",
+  "4": " ",
+  "5": "<null>",
+  "6": "ㄷ",
+  "7": "ㄹ",
+  "8": "ㅁ",
+  "9": "ㅂ",
+  "10": "ㅅ",
+  "11": "ㅈ",
+  "12": "ㅊ",
+  "13": "ㅋ",
+  "14": "ㅌ",
+  "15": "ㅍ",
+  "16": "ㅎ",
+  "17": "ㅏ",
+  "18": "ㅐ",
+  "19": "ㅓ",
+  "20": "ㅔ",
+  "21": "ㅗ",
+  "22": "ㅚ",
+  "23": "ㅜ",
+  "24": "ㅟ",
+  "25": "ㅡ",
+  "26": "ㅣ",
+  "27": "ㅑ",
+  "28": "ㅒ",
+  "29": "ㅕ",
+  "30": "ㅖ",
+  "31": "ㅘ",
+  "32": "ㅙ",
+  "33": "ㅛ",
+  "34": "ㅝ",
+  "35": "ㅞ",
+  "36": "ㅠ",
+  "37": "ㅢ",
+  "38": "ㄴ",
+  "39": "ㅇ",
+  "40": "ㄱ",
+  "41": "ㄸ",
+  "42": "ㅃ",
+  "43": "ㅉ",
+  "44": "ㄳ",
+  "45": "ㄵ",
+  "46": "ㄶ",
+  "47": "ㄺ",
+  "48": "ㄻ",
+  "49": "ㄽ",
+  "50": "ㄾ",
+  "51": "ㄿ",
+  "52": "ㅀ",
+  "53": "ㅆ",
+  "54": "ㄲ"
+}

tokenizers/s_vocab.json

@@ -0,0 +1,1209 @@
+{
+  "0": "<s>",
+  "1": "</s>",
+  "2": "<pad>",
+  "3": "<unk>",
+  "4": " ",
+  "5": "는",
+  "6": "이",
+  "7": "을",
+  "8": "하",
+  "9": "고",
+  "10": "에",
+  "11": "의",
+  "12": "지",
+  "13": "은",
+  "14": "사",
+  "15": "로",
+  "16": "를",
+  "17": "한",
+  "18": "가",
+  "19": "대",
+  "20": "서",
+  "21": "니",
+  "22": "있",
+  "23": "기",
+  "24": "들",
+  "25": "으",
+  "26": "정",
+  "27": "자",
+  "28": "했",
+  "29": "도",
+  "30": "부",
+  "31": "아",
+  "32": "시",
+  "33": "어",
+  "34": "리",
+  "35": "십",
+  "36": "보",
+  "37": "그",
+  "38": "인",
+  "39": "수",
+  "40": "라",
+  "41": "전",
+  "42": "게",
+  "43": "것",
+  "44": "주",
+  "45": "원",
+  "46": "장",
+  "47": "해",
+  "48": "제",
+  "49": "나",
+  "50": "습",
+  "51": "상",
+  "52": "일",
+  "53": "국",
+  "54": "구",
+  "55": "문",
+  "56": "적",
+  "57": "여",
+  "58": "경",
+  "59": "성",
+  "60": "만",
+  "61": "면",
+  "62": "과",
+  "63": "공",
+  "64": "동",
+  "65": "당",
+  "66": "위",
+  "67": "소",
+  "68": "스",
+  "69": "비",
+  "70": "거",
+  "71": "요",
+  "72": "오",
+  "73": "었",
+  "74": "관",
+  "75": "내",
+  "76": "조",
+  "77": "천",
+  "78": "중",
+  "79": "신",
+  "80": "무",
+  "81": "마",
+  "82": "통",
+  "83": "명",
+  "84": "우",
+  "85": "계",
+  "86": "미",
+  "87": "실",
+  "88": "입",
+  "89": "생",
+  "90": "모",
+  "91": "유",
+  "92": "않",
+  "93": "세",
+  "94": "되",
+  "95": "회",
+  "96": "치",
+  "97": "할",
+  "98": "러",
+  "99": "와",
+  "100": "말",
+  "101": "없",
+  "102": "까",
+  "103": "진",
+  "104": "분",
+  "105": "선",
+  "106": "화",
+  "107": "려",
+  "108": "개",
+  "109": "재",
+  "110": "발",
+  "111": "용",
+  "112": "연",
+  "113": "업",
+  "114": "년",
+  "115": "안",
+  "116": "교",
+  "117": "받",
+  "118": "단",
+  "119": "백",
+  "120": "방",
+  "121": "행",
+  "122": "며",
+  "123": "트",
+  "124": "민",
+  "125": "데",
+  "126": "영",
+  "127": "결",
+  "128": "때",
+  "129": "표",
+  "130": "씨",
+  "131": "출",
+  "132": "반",
+  "133": "바",
+  "134": "학",
+  "135": "최",
+  "136": "직",
+  "137": "람",
+  "138": "불",
+  "139": "현",
+  "140": "금",
+  "141": "등",
+  "142": "심",
+  "143": "호",
+  "144": "차",
+  "145": "예",
+  "146": "물",
+  "147": "산",
+  "148": "았",
+  "149": "청",
+  "150": "르",
+  "151": "히",
+  "152": "체",
+  "153": "임",
+  "154": "각",
+  "155": "강",
+  "156": "합",
+  "157": "된",
+  "158": "남",
+  "159": "식",
+  "160": "역",
+  "161": "판",
+  "162": "처",
+  "163": "던",
+  "164": "터",
+  "165": "삼",
+  "166": "간",
+  "167": "건",
+  "168": "박",
+  "169": "작",
+  "170": "법",
+  "171": "센",
+  "172": "매",
+  "173": "감",
+  "174": "노",
+  "175": "야",
+  "176": "많",
+  "177": "드",
+  "178": "됐",
+  "179": "찰",
+  "180": "달",
+  "181": "퍼",
+  "182": "특",
+  "183": "피",
+  "184": "증",
+  "185": "김",
+  "186": "같",
+  "187": "력",
+  "188": "배",
+  "189": "양",
+  "190": "점",
+  "191": "겠",
+  "192": "음",
+  "193": "알",
+  "194": "권",
+  "195": "후",
+  "196": "령",
+  "197": "집",
+  "198": "저",
+  "199": "속",
+  "200": "졌",
+  "201": "태",
+  "202": "설",
+  "203": "월",
+  "204": "두",
+  "205": "파",
+  "206": "추",
+  "207": "포",
+  "208": "른",
+  "209": "따",
+  "210": "새",
+  "211": "함",
+  "212": "였",
+  "213": "타",
+  "214": "능",
+  "215": "칠",
+  "216": "종",
+  "217": "육",
+  "218": "운",
+  "219": "병",
+  "220": "급",
+  "221": "확",
+  "222": "근",
+  "223": "난",
+  "224": "검",
+  "225": "언",
+  "226": "더",
+  "227": "느",
+  "228": "런",
+  "229": "료",
+  "230": "변",
+  "231": "석",
+  "232": "누",
+  "233": "견",
+  "234": "본",
+  "235": "준",
+  "236": "황",
+  "237": "팔",
+  "238": "살",
+  "239": "평",
+  "240": "래",
+  "241": "올",
+  "242": "목",
+  "243": "외",
+  "244": "열",
+  "245": "격",
+  "246": "북",
+  "247": "크",
+  "248": "울",
+  "249": "질",
+  "250": "활",
+  "251": "렇",
+  "252": "총",
+  "253": "앞",
+  "254": "쩜",
+  "255": "못",
+  "256": "돌",
+  "257": "든",
+  "258": "필",
+  "259": "책",
+  "260": "담",
+  "261": "복",
+  "262": "레",
+  "263": "초",
+  "264": "카",
+  "265": "투",
+  "266": "형",
+  "267": "승",
+  "268": "번",
+  "269": "곳",
+  "270": "머",
+  "271": "향",
+  "272": "환",
+  "273": "버",
+  "274": "왔",
+  "275": "항",
+  "276": "섯",
+  "277": "밝",
+  "278": "별",
+  "279": "될",
+  "280": "약",
+  "281": "키",
+  "282": "론",
+  "283": "날",
+  "284": "군",
+  "285": "편",
+  "286": "록",
+  "287": "높",
+  "288": "께",
+  "289": "취",
+  "290": "손",
+  "291": "량",
+  "292": "품",
+  "293": "줄",
+  "294": "측",
+  "295": "참",
+  "296": "폭",
+  "297": "놓",
+  "298": "디",
+  "299": "프",
+  "300": "규",
+  "301": "벌",
+  "302": "순",
+  "303": "늘",
+  "304": "냐",
+  "305": "침",
+  "306": "혔",
+  "307": "절",
+  "308": "망",
+  "309": "린",
+  "310": "또",
+  "311": "넘",
+  "312": "련",
+  "313": "님",
+  "314": "렸",
+  "315": "온",
+  "316": "술",
+  "317": "족",
+  "318": "맞",
+  "319": "광",
+  "320": "났",
+  "321": "택",
+  "322": "험",
+  "323": "걸",
+  "324": "토",
+  "325": "란",
+  "326": "송",
+  "327": "잡",
+  "328": "찾",
+  "329": "루",
+  "330": "겨",
+  "331": "논",
+  "332": "억",
+  "333": "충",
+  "334": "협",
+  "335": "창",
+  "336": "애",
+  "337": "메",
+  "338": "움",
+  "339": "축",
+  "340": "워",
+  "341": "네",
+  "342": "져",
+  "343": "응",
+  "344": "좋",
+  "345": "친",
+  "346": "름",
+  "347": "접",
+  "348": "락",
+  "349": "독",
+  "350": "혹",
+  "351": "티",
+  "352": "완",
+  "353": "베",
+  "354": "철",
+  "355": "럼",
+  "356": "악",
+  "357": "범",
+  "358": "액",
+  "359": "막",
+  "360": "쓰",
+  "361": "밀",
+  "362": "코",
+  "363": "돼",
+  "364": "떤",
+  "365": "커",
+  "366": "페",
+  "367": "패",
+  "368": "떻",
+  "369": "휴",
+  "370": "극",
+  "371": "떨",
+  "372": "허",
+  "373": "죠",
+  "374": "례",
+  "375": "눈",
+  "376": "힘",
+  "377": "퇴",
+  "378": "답",
+  "379": "너",
+  "380": "희",
+  "381": "획",
+  "382": "곱",
+  "383": "익",
+  "384": "탈",
+  "385": "브",
+  "386": "흔",
+  "387": "헌",
+  "388": "붙",
+  "389": "밖",
+  "390": "채",
+  "391": "몰",
+  "392": "돈",
+  "393": "길",
+  "394": "녀",
+  "395": "떠",
+  "396": "먹",
+  "397": "득",
+  "398": "빠",
+  "399": "혜",
+  "400": "류",
+  "401": "뉴",
+  "402": "탄",
+  "403": "율",
+  "404": "셨",
+  "405": "잘",
+  "406": "얘",
+  "407": "끝",
+  "408": "큰",
+  "409": "쟁",
+  "410": "갔",
+  "411": "징",
+  "412": "롯",
+  "413": "착",
+  "414": "테",
+  "415": "및",
+  "416": "뒤",
+  "417": "슬",
+  "418": "갈",
+  "419": "풍",
+  "420": "객",
+  "421": "혐",
+  "422": "귀",
+  "423": "혼",
+  "424": "림",
+  "425": "죄",
+  "426": "잠",
+  "427": "씀",
+  "428": "싶",
+  "429": "숨",
+  "430": "큼",
+  "431": "농",
+  "432": "먼",
+  "433": "염",
+  "434": "풀",
+  "435": "혁",
+  "436": "갖",
+  "437": "홍",
+  "438": "뤄",
+  "439": "존",
+  "440": "왕",
+  "441": "찬",
+  "442": "꾸",
+  "443": "뿐",
+  "444": "플",
+  "445": "얼",
+  "446": "끌",
+  "447": "좌",
+  "448": "닌",
+  "449": "핵",
+  "450": "률",
+  "451": "앙",
+  "452": "긴",
+  "453": "봉",
+  "454": "낸",
+  "455": "냈",
+  "456": "혀",
+  "457": "글",
+  "458": "암",
+  "459": "립",
+  "460": "욕",
+  "461": "몇",
+  "462": "좀",
+  "463": "끼",
+  "464": "폐",
+  "465": "효",
+  "466": "압",
+  "467": "됩",
+  "468": "덟",
+  "469": "믿",
+  "470": "촉",
+  "471": "엄",
+  "472": "싸",
+  "473": "쉽",
+  "474": "홉",
+  "475": "팀",
+  "476": "죽",
+  "477": "균",
+  "478": "럽",
+  "479": "엔",
+  "480": "랑",
+  "481": "숙",
+  "482": "골",
+  "483": "째",
+  "484": "얻",
+  "485": "렵",
+  "486": "쿠",
+  "487": "납",
+  "488": "층",
+  "489": "겁",
+  "490": "윤",
+  "491": "뜻",
+  "492": "놀",
+  "493": "쳤",
+  "494": "랜",
+  "495": "릴",
+  "496": "융",
+  "497": "둔",
+  "498": "젊",
+  "499": "룹",
+  "500": "쳐",
+  "501": "휘",
+  "502": "낙",
+  "503": "옮",
+  "504": "줬",
+  "505": "씩",
+  "506": "색",
+  "507": "깨",
+  "508": "걱",
+  "509": "쪽",
+  "510": "케",
+  "511": "짜",
+  "512": "켜",
+  "513": "칙",
+  "514": "봤",
+  "515": "슨",
+  "516": "흐",
+  "517": "털",
+  "518": "곡",
+  "519": "굴",
+  "520": "맡",
+  "521": "랐",
+  "522": "웠",
+  "523": "듣",
+  "524": "략",
+  "525": "낮",
+  "526": "엇",
+  "527": "즈",
+  "528": "몸",
+  "529": "덕",
+  "530": "볼",
+  "531": "뛰",
+  "532": "꼽",
+  "533": "빨",
+  "534": "옥",
+  "535": "훈",
+  "536": "묻",
+  "537": "첫",
+  "538": "앵",
+  "539": "벗",
+  "540": "컨",
+  "541": "맥",
+  "542": "틀",
+  "543": "웨",
+  "544": "홀",
+  "545": "클",
+  "546": "섰",
+  "547": "꽃",
+  "548": "덧",
+  "549": "값",
+  "550": "욱",
+  "551": "잃",
+  "552": "텐",
+  "553": "흘",
+  "554": "램",
+  "555": "쌓",
+  "556": "킬",
+  "557": "헤",
+  "558": "짓",
+  "559": "웃",
+  "560": "듯",
+  "561": "벽",
+  "562": "럭",
+  "563": "렀",
+  "564": "잔",
+  "565": "쉬",
+  "566": "닥",
+  "567": "뷰",
+  "568": "롭",
+  "569": "녹",
+  "570": "힌",
+  "571": "칼",
+  "572": "랫",
+  "573": "둘",
+  "574": "괴",
+  "575": "갑",
+  "576": "쏟",
+  "577": "빼",
+  "578": "겼",
+  "579": "뀌",
+  "580": "쉰",
+  "581": "잇",
+  "582": "빌",
+  "583": "훼",
+  "584": "흥",
+  "585": "냉",
+  "586": "뢰",
+  "587": "탕",
+  "588": "핑",
+  "589": "빈",
+  "590": "늦",
+  "591": "졸",
+  "592": "왜",
+  "593": "혈",
+  "594": "춰",
+  "595": "낼",
+  "596": "슈",
+  "597": "쇄",
+  "598": "뜨",
+  "599": "끊",
+  "600": "슷",
+  "601": "넷",
+  "602": "깊",
+  "603": "딸",
+  "604": "줘",
+  "605": "봐",
+  "606": "땅",
+  "607": "캐",
+  "608": "렌",
+  "609": "덮",
+  "610": "짐",
+  "611": "겪",
+  "612": "궁",
+  "613": "폰",
+  "614": "밤",
+  "615": "닙",
+  "616": "빛",
+  "617": "싼",
+  "618": "꺼",
+  "619": "곤",
+  "620": "쯤",
+  "621": "냥",
+  "622": "쇼",
+  "623": "찌",
+  "624": "칭",
+  "625": "즐",
+  "626": "블",
+  "627": "잖",
+  "628": "튼",
+  "629": "척",
+  "630": "델",
+  "631": "굳",
+  "632": "띄",
+  "633": "셈",
+  "634": "겹",
+  "635": "텔",
+  "636": "낌",
+  "637": "콘",
+  "638": "츠",
+  "639": "뒷",
+  "640": "맛",
+  "641": "멀",
+  "642": "쇠",
+  "643": "묵",
+  "644": "쏠",
+  "645": "솔",
+  "646": "쏘",
+  "647": "섭",
+  "648": "슴",
+  "649": "펼",
+  "650": "탁",
+  "651": "뿌",
+  "652": "멸",
+  "653": "낳",
+  "654": "빚",
+  "655": "쓴",
+  "656": "뚜",
+  "657": "앉",
+  "658": "훨",
+  "659": "씬",
+  "660": "펴",
+  "661": "찍",
+  "662": "줍",
+  "663": "즉",
+  "664": "흡",
+  "665": "념",
+  "666": "쩌",
+  "667": "촬",
+  "668": "촌",
+  "669": "앗",
+  "670": "팅",
+  "671": "묘",
+  "672": "캠",
+  "673": "엘",
+  "674": "륙",
+  "675": "랍",
+  "676": "굉",
+  "677": "뒀",
+  "678": "뭐",
+  "679": "럴",
+  "680": "랬",
+  "681": "넣",
+  "682": "밥",
+  "683": "푸",
+  "684": "섬",
+  "685": "똑",
+  "686": "넓",
+  "687": "춘",
+  "688": "촛",
+  "689": "셔",
+  "690": "썼",
+  "691": "옷",
+  "692": "벨",
+  "693": "챙",
+  "694": "턴",
+  "695": "멘",
+  "696": "템",
+  "697": "즘",
+  "698": "녔",
+  "699": "벼",
+  "700": "션",
+  "701": "릅",
+  "702": "흰",
+  "703": "홈",
+  "704": "컷",
+  "705": "셜",
+  "706": "봅",
+  "707": "딱",
+  "708": "쨌",
+  "709": "둥",
+  "710": "괄",
+  "711": "셀",
+  "712": "멈",
+  "713": "뼈",
+  "714": "덜",
+  "715": "켓",
+  "716": "킨",
+  "717": "뮤",
+  "718": "므",
+  "719": "쓸",
+  "720": "팎",
+  "721": "렴",
+  "722": "써",
+  "723": "껑",
+  "724": "윗",
+  "725": "롱",
+  "726": "즌",
+  "727": "흑",
+  "728": "덤",
+  "729": "딩",
+  "730": "걷",
+  "731": "널",
+  "732": "닉",
+  "733": "깎",
+  "734": "셋",
+  "735": "휩",
+  "736": "깝",
+  "737": "링",
+  "738": "콩",
+  "739": "닫",
+  "740": "닷",
+  "741": "몬",
+  "742": "벤",
+  "743": "땐",
+  "744": "탑",
+  "745": "읽",
+  "746": "섞",
+  "747": "숭",
+  "748": "놈",
+  "749": "첩",
+  "750": "곧",
+  "751": "둑",
+  "752": "깔",
+  "753": "붕",
+  "754": "횡",
+  "755": "짝",
+  "756": "앓",
+  "757": "붉",
+  "758": "햇",
+  "759": "컸",
+  "760": "옹",
+  "761": "삭",
+  "762": "숲",
+  "763": "툼",
+  "764": "짧",
+  "765": "릭",
+  "766": "묶",
+  "767": "훌",
+  "768": "캘",
+  "769": "닿",
+  "770": "꿈",
+  "771": "돕",
+  "772": "뭔",
+  "773": "켰",
+  "774": "핀",
+  "775": "옵",
+  "776": "컵",
+  "777": "뻔",
+  "778": "낀",
+  "779": "롤",
+  "780": "닝",
+  "781": "싱",
+  "782": "꼼",
+  "783": "듬",
+  "784": "맨",
+  "785": "첨",
+  "786": "탓",
+  "787": "틴",
+  "788": "뇌",
+  "789": "깁",
+  "790": "끄",
+  "791": "맹",
+  "792": "쁘",
+  "793": "떼",
+  "794": "톤",
+  "795": "곁",
+  "796": "뱀",
+  "797": "톡",
+  "798": "쾌",
+  "799": "꼬",
+  "800": "갚",
+  "801": "꿀",
+  "802": "싫",
+  "803": "듭",
+  "804": "짚",
+  "805": "픈",
+  "806": "칸",
+  "807": "옆",
+  "808": "뚝",
+  "809": "뽑",
+  "810": "빗",
+  "811": "앤",
+  "812": "곰",
+  "813": "팡",
+  "814": "엎",
+  "815": "겸",
+  "816": "콜",
+  "817": "겐",
+  "818": "옛",
+  "819": "팽",
+  "820": "렘",
+  "821": "끔",
+  "822": "뇨",
+  "823": "짙",
+  "824": "첼",
+  "825": "솟",
+  "826": "탐",
+  "827": "떡",
+  "828": "맺",
+  "829": "꿨",
+  "830": "빅",
+  "831": "힐",
+  "832": "넥",
+  "833": "릿",
+  "834": "띠",
+  "835": "몫",
+  "836": "빙",
+  "837": "긋",
+  "838": "렛",
+  "839": "쥐",
+  "840": "쌍",
+  "841": "멋",
+  "842": "닭",
+  "843": "꼭",
+  "844": "헬",
+  "845": "샤",
+  "846": "캉",
+  "847": "낡",
+  "848": "갤",
+  "849": "엿",
+  "850": "멍",
+  "851": "룬",
+  "852": "닐",
+  "853": "껴",
+  "854": "킹",
+  "855": "몽",
+  "856": "콧",
+  "857": "컴",
+  "858": "팜",
+  "859": "랭",
+  "860": "빵",
+  "861": "뤘",
+  "862": "촘",
+  "863": "밴",
+  "864": "잊",
+  "865": "꼈",
+  "866": "웅",
+  "867": "춤",
+  "868": "꼴",
+  "869": "끓",
+  "870": "씌",
+  "871": "륭",
+  "872": "칩",
+  "873": "텍",
+  "874": "륜",
+  "875": "킷",
+  "876": "덩",
+  "877": "쁜",
+  "878": "밑",
+  "879": "캔",
+  "880": "끈",
+  "881": "앱",
+  "882": "옳",
+  "883": "랙",
+  "884": "셉",
+  "885": "윈",
+  "886": "콤",
+  "887": "볕",
+  "888": "흉",
+  "889": "퀴",
+  "890": "삶",
+  "891": "엑",
+  "892": "괌",
+  "893": "놨",
+  "894": "넌",
+  "895": "쥔",
+  "896": "갠",
+  "897": "긍",
+  "898": "껏",
+  "899": "렁",
+  "900": "잉",
+  "901": "냄",
+  "902": "깃",
+  "903": "룸",
+  "904": "앨",
+  "905": "헐",
+  "906": "쿡",
+  "907": "랄",
+  "908": "늬",
+  "909": "얹",
+  "910": "퓨",
+  "911": "봄",
+  "912": "깡",
+  "913": "렉",
+  "914": "눠",
+  "915": "녕",
+  "916": "샌",
+  "917": "쌀",
+  "918": "겉",
+  "919": "흩",
+  "920": "큐",
+  "921": "낯",
+  "922": "룡",
+  "923": "탱",
+  "924": "댓",
+  "925": "뀐",
+  "926": "꿰",
+  "927": "튿",
+  "928": "팻",
+  "929": "틸",
+  "930": "뎅",
+  "931": "꽁",
+  "932": "닛",
+  "933": "뱅",
+  "934": "끗",
+  "935": "쪼",
+  "936": "웹",
+  "937": "꿔",
+  "938": "릎",
+  "939": "딜",
+  "940": "펜",
+  "941": "낭",
+  "942": "쩔",
+  "943": "꾼",
+  "944": "칫",
+  "945": "쁩",
+  "946": "쿄",
+  "947": "렬",
+  "948": "뭘",
+  "949": "쫓",
+  "950": "푼",
+  "951": "잭",
+  "952": "츰",
+  "953": "찢",
+  "954": "릉",
+  "955": "넛",
+  "956": "뱃",
+  "957": "멧",
+  "958": "샐",
+  "959": "뺏",
+  "960": "딪",
+  "961": "렷",
+  "962": "뻘",
+  "963": "덴",
+  "964": "폴",
+  "965": "롬",
+  "966": "켈",
+  "967": "셰",
+  "968": "핏",
+  "969": "괭",
+  "970": "팬",
+  "971": "뻗",
+  "972": "슐",
+  "973": "젠",
+  "974": "젝",
+  "975": "궤",
+  "976": "냇",
+  "977": "헴",
+  "978": "돋",
+  "979": "씁",
+  "980": "밭",
+  "981": "뚫",
+  "982": "풋",
+  "983": "쩍",
+  "984": "푹",
+  "985": "밌",
+  "986": "튀",
+  "987": "폼",
+  "988": "웬",
+  "989": "쑤",
+  "990": "섣",
+  "991": "갯",
+  "992": "돛",
+  "993": "젖",
+  "994": "젓",
+  "995": "좁",
+  "996": "찔",
+  "997": "껍",
+  "998": "쿨",
+  "999": "엉",
+  "1000": "콥",
+  "1001": "땄",
+  "1002": "엽",
+  "1003": "튜",
+  "1004": "맘",
+  "1005": "왼",
+  "1006": "썩",
+  "1007": "읍",
+  "1008": "굿",
+  "1009": "퉁",
+  "1010": "팩",
+  "1011": "넨",
+  "1012": "찮",
+  "1013": "젼",
+  "1014": "븐",
+  "1015": "잣",
+  "1016": "흙",
+  "1017": "땠",
+  "1018": "솥",
+  "1019": "뷔",
+  "1020": "폄",
+  "1021": "궈",
+  "1022": "꽂",
+  "1023": "녁",
+  "1024": "탠",
+  "1025": "꽥",
+  "1026": "펄",
+  "1027": "짖",
+  "1028": "벚",
+  "1029": "섹",
+  "1030": "닳",
+  "1031": "펀",
+  "1032": "갱",
+  "1033": "삽",
+  "1034": "삿",
+  "1035": "틱",
+  "1036": "늪",
+  "1037": "뤼",
+  "1038": "뿜",
+  "1039": "얽",
+  "1040": "씻",
+  "1041": "쥘",
+  "1042": "잦",
+  "1043": "컥",
+  "1044": "팰",
+  "1045": "믹",
+  "1046": "밍",
+  "1047": "딴",
+  "1048": "띤",
+  "1049": "떴",
+  "1050": "깬",
+  "1051": "펌",
+  "1052": "딨",
+  "1053": "낫",
+  "1054": "뺑",
+  "1055": "컫",
+  "1056": "엷",
+  "1057": "폈",
+  "1058": "펠",
+  "1059": "겟",
+  "1060": "픽",
+  "1061": "뺀",
+  "1062": "뺌",
+  "1063": "눌",
+  "1064": "딥",
+  "1065": "챌",
+  "1066": "썰",
+  "1067": "볶",
+  "1068": "샷",
+  "1069": "꿇",
+  "1070": "삐",
+  "1071": "쉼",
+  "1072": "볍",
+  "1073": "덫",
+  "1074": "띵",
+  "1075": "똥",
+  "1076": "쌈",
+  "1077": "엡",
+  "1078": "쇤",
+  "1079": "괘",
+  "1080": "씸",
+  "1081": "쳇",
+  "1082": "숍",
+  "1083": "굵",
+  "1084": "잰",
+  "1085": "됨",
+  "1086": "뵙",
+  "1087": "텃",
+  "1088": "륵",
+  "1089": "딘",
+  "1090": "헷",
+  "1091": "퓰",
+  "1092": "릇",
+  "1093": "녘",
+  "1094": "벳",
+  "1095": "핫",
+  "1096": "뻐",
+  "1097": "봇",
+  "1098": "늠",
+  "1099": "뎌",
+  "1100": "뉜",
+  "1101": "샀",
+  "1102": "붐",
+  "1103": "볐",
+  "1104": "툴",
+  "1105": "쌌",
+  "1106": "샘",
+  "1107": "쿼",
+  "1108": "톨",
+  "1109": "띨",
+  "1110": "랴",
+  "1111": "젤",
+  "1112": "펫",
+  "1113": "냅",
+  "1114": "쫄",
+  "1115": "픔",
+  "1116": "땡",
+  "1117": "첸",
+  "1118": "닦",
+  "1119": "톰",
+  "1120": "얇",
+  "1121": "잎",
+  "1122": "궐",
+  "1123": "땀",
+  "1124": "굽",
+  "1125": "붓",
+  "1126": "갓",
+  "1127": "곽",
+  "1128": "윌",
+  "1129": "댐",
+  "1130": "맏",
+  "1131": "엣",
+  "1132": "웁",
+  "1133": "뛴",
+  "1134": "돗",
+  "1135": "챔",
+  "1136": "끽",
+  "1137": "둬",
+  "1138": "옴",
+  "1139": "싹",
+  "1140": "뇽",
+  "1141": "헨",
+  "1142": "멜",
+  "1143": "곶",
+  "1144": "굶",
+  "1145": "왈",
+  "1146": "뭇",
+  "1147": "탬",
+  "1148": "꿎",
+  "1149": "샬",
+  "1150": "댁",
+  "1151": "돔",
+  "1152": "맑",
+  "1153": "띔",
+  "1154": "텼",
+  "1155": "턱",
+  "1156": "엠",
+  "1157": "깥",
+  "1158": "헝",
+  "1159": "샵",
+  "1160": "닮",
+  "1161": "챠",
+  "1162": "늉",
+  "1163": "켑",
+  "1164": "믈",
+  "1165": "꽝",
+  "1166": "텅",
+  "1167": "룰",
+  "1168": "듀",
+  "1169": "뵈",
+  "1170": "촨",
+  "1171": "끅",
+  "1172": "뭄",
+  "1173": "뗄",
+  "1174": "둠",
+  "1175": "짊",
+  "1176": "얗",
+  "1177": "흠",
+  "1178": "뻑",
+  "1179": "벅",
+  "1180": "킥",
+  "1181": "잽",
+  "1182": "뜸",
+  "1183": "찻",
+  "1184": "뮬",
+  "1185": "팍",
+  "1186": "뜯",
+  "1187": "쥬",
+  "1188": "찧",
+  "1189": "솜",
+  "1190": "넉",
+  "1191": "윙",
+  "1192": "맙",
+  "1193": "밋",
+  "1194": "핸",
+  "1195": "멕",
+  "1196": "짬",
+  "1197": "뽕",
+  "1198": "쏜",
+  "1199": "틈",
+  "1200": "뽀",
+  "1201": "튬",
+  "1202": "켐",
+  "1203": "젋",
+  "1204": "쭉",
+  "1205": "훤",
+  "1206": "다"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a04bd7d49f246007fe68db640ec39ac0197abfd25a63c76db53fd274cc20f8
+size 4923