Upload WavLMForSequenceClassification

config.json

@@ -0,0 +1,374 @@
+{
+  "_name_or_path": "wavlm-large",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "WavLMForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "finetuning_task": "audio-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "A canoon",
+    "1": "A cinj",
+    "2": "A keen",
+    "3": "A lanq",
+    "4": "A \u00f1aa\u01b4",
+    "5": "A \u00f1amaak",
+    "6": "Alaa",
+    "7": "Bacaac",
+    "8": "Benn",
+    "9": "B\u00e1lamuk",
+    "10": "B\u00fabaar",
+    "11": "Caggal",
+    "12": "Ceme",
+    "13": "Ci ginnaaw",
+    "14": "Ci kanam",
+    "15": "Ci kow",
+    "16": "Ci suuf",
+    "17": "C\u00e0mmo\u00f1",
+    "18": "Darnde",
+    "19": "Dow",
+    "20": "Doxal",
+    "21": "D\u00e9edet",
+    "22": "Eey",
+    "23": "Esuwa",
+    "24": "Eyen",
+    "25": "E\u00e9",
+    "26": "Fatiya",
+    "27": "Fukk",
+    "28": "Funoom",
+    "29": "Futok",
+    "30": "Futok di sibaakiir",
+    "31": "Futok di sigaba",
+    "32": "Futok di s\u00edfeejir",
+    "33": "Futok di y\u00e1kon",
+    "34": "F\u00e1cul",
+    "35": "Garab",
+    "36": "Goo",
+    "37": "Hani",
+    "38": "Jaay",
+    "39": "Jeegom",
+    "40": "Jeenay",
+    "41": "Jeetati",
+    "42": "Jee\u0257i\u0257i",
+    "43": "Jik",
+    "44": "Jiku",
+    "45": "Joy",
+    "46": "Juni",
+    "47": "Junne",
+    "48": "Juroom",
+    "49": "Juroom-benn",
+    "50": "Juroom-\u00f1aar",
+    "51": "Juroom-\u00f1eent",
+    "52": "Juroom-\u00f1ett",
+    "53": "J\u00ebnd",
+    "54": "Kakamben",
+    "55": "Kamay",
+    "56": "Kanoomen",
+    "57": "K\u00e1kambul",
+    "58": "K\u00e1rir",
+    "59": "Lal",
+    "60": "Lees",
+    "61": "Leng",
+    "62": "Le\u0257ki",
+    "63": "Li",
+    "64": "Mbaamir",
+    "65": "Mbalndi",
+    "66": "Nano",
+    "67": "Naxik",
+    "68": "Nay",
+    "69": "Ndaxar",
+    "70": "Ndeyjoor",
+    "71": "Ndiga",
+    "72": "Ndii\u01ad",
+    "73": "Njong",
+    "74": "O \u0253ox",
+    "75": "Picc",
+    "76": "Rawaandu",
+    "77": "Sappo",
+    "78": "Sibaakiir",
+    "79": "Sigaba",
+    "80": "Solndu",
+    "81": "Soodde",
+    "82": "S\u00edfeejir",
+    "83": "Tadik",
+    "84": "Tati",
+    "85": "Taxawal",
+    "86": "Teemedere",
+    "87": "Teemeed",
+    "88": "Tentaam",
+    "89": "Tik",
+    "90": "Took",
+    "91": "Tus",
+    "92": "T\u00e9emeer",
+    "93": "Ub /T\u00ebj",
+    "94": "Ub/T\u00ebj",
+    "95": "Ubbi /Tijji",
+    "96": "Udditde",
+    "97": "Uddude",
+    "98": "Ujaw",
+    "99": "Ujunere",
+    "100": "Ujuum",
+    "101": "U\u00f1en",
+    "102": "Waafulet",
+    "103": "Waaw",
+    "104": "Weg",
+    "105": "Wet",
+    "106": "W\u00fali",
+    "107": "Xa-aa",
+    "108": "Xaj",
+    "109": "Xar\u0253axay",
+    "110": "Yahdu",
+    "111": "Yeeso",
+    "112": "Yeeyde",
+    "113": "Y\u00e1kon",
+    "114": "\u00d1aamo",
+    "115": "\u00d1aar",
+    "116": "\u00d1eent",
+    "117": "\u00d1ett",
+    "118": "\u018ai\u0257i",
+    "119": "\u01a4etaa-fo-leng",
+    "120": "\u01a4etaa-naxak",
+    "121": "\u01a4etaa-tadak",
+    "122": "\u01a4etaa-\u01adaq",
+    "123": "\u01a4etik"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "A canoon": "0",
+    "A cinj": "1",
+    "A keen": "2",
+    "A lanq": "3",
+    "A \u00f1aa\u01b4": "4",
+    "A \u00f1amaak": "5",
+    "Alaa": "6",
+    "Bacaac": "7",
+    "Benn": "8",
+    "B\u00e1lamuk": "9",
+    "B\u00fabaar": "10",
+    "Caggal": "11",
+    "Ceme": "12",
+    "Ci ginnaaw": "13",
+    "Ci kanam": "14",
+    "Ci kow": "15",
+    "Ci suuf": "16",
+    "C\u00e0mmo\u00f1": "17",
+    "Darnde": "18",
+    "Dow": "19",
+    "Doxal": "20",
+    "D\u00e9edet": "21",
+    "Eey": "22",
+    "Esuwa": "23",
+    "Eyen": "24",
+    "E\u00e9": "25",
+    "Fatiya": "26",
+    "Fukk": "27",
+    "Funoom": "28",
+    "Futok": "29",
+    "Futok di sibaakiir": "30",
+    "Futok di sigaba": "31",
+    "Futok di s\u00edfeejir": "32",
+    "Futok di y\u00e1kon": "33",
+    "F\u00e1cul": "34",
+    "Garab": "35",
+    "Goo": "36",
+    "Hani": "37",
+    "Jaay": "38",
+    "Jeegom": "39",
+    "Jeenay": "40",
+    "Jeetati": "41",
+    "Jee\u0257i\u0257i": "42",
+    "Jik": "43",
+    "Jiku": "44",
+    "Joy": "45",
+    "Juni": "46",
+    "Junne": "47",
+    "Juroom": "48",
+    "Juroom-benn": "49",
+    "Juroom-\u00f1aar": "50",
+    "Juroom-\u00f1eent": "51",
+    "Juroom-\u00f1ett": "52",
+    "J\u00ebnd": "53",
+    "Kakamben": "54",
+    "Kamay": "55",
+    "Kanoomen": "56",
+    "K\u00e1kambul": "57",
+    "K\u00e1rir": "58",
+    "Lal": "59",
+    "Lees": "60",
+    "Leng": "61",
+    "Le\u0257ki": "62",
+    "Li": "63",
+    "Mbaamir": "64",
+    "Mbalndi": "65",
+    "Nano": "66",
+    "Naxik": "67",
+    "Nay": "68",
+    "Ndaxar": "69",
+    "Ndeyjoor": "70",
+    "Ndiga": "71",
+    "Ndii\u01ad": "72",
+    "Njong": "73",
+    "O \u0253ox": "74",
+    "Picc": "75",
+    "Rawaandu": "76",
+    "Sappo": "77",
+    "Sibaakiir": "78",
+    "Sigaba": "79",
+    "Solndu": "80",
+    "Soodde": "81",
+    "S\u00edfeejir": "82",
+    "Tadik": "83",
+    "Tati": "84",
+    "Taxawal": "85",
+    "Teemedere": "86",
+    "Teemeed": "87",
+    "Tentaam": "88",
+    "Tik": "89",
+    "Took": "90",
+    "Tus": "91",
+    "T\u00e9emeer": "92",
+    "Ub /T\u00ebj": "93",
+    "Ub/T\u00ebj": "94",
+    "Ubbi /Tijji": "95",
+    "Udditde": "96",
+    "Uddude": "97",
+    "Ujaw": "98",
+    "Ujunere": "99",
+    "Ujuum": "100",
+    "U\u00f1en": "101",
+    "Waafulet": "102",
+    "Waaw": "103",
+    "Weg": "104",
+    "Wet": "105",
+    "W\u00fali": "106",
+    "Xa-aa": "107",
+    "Xaj": "108",
+    "Xar\u0253axay": "109",
+    "Yahdu": "110",
+    "Yeeso": "111",
+    "Yeeyde": "112",
+    "Y\u00e1kon": "113",
+    "\u00d1aamo": "114",
+    "\u00d1aar": "115",
+    "\u00d1eent": "116",
+    "\u00d1ett": "117",
+    "\u018ai\u0257i": "118",
+    "\u01a4etaa-fo-leng": "119",
+    "\u01a4etaa-naxak": "120",
+    "\u01a4etaa-tadak": "121",
+    "\u01a4etaa-\u01adaq": "122",
+    "\u01a4etik": "123"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "max_bucket_distance": 800,
+  "model_type": "wavlm",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "replace_prob": 0.5,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008f1386f433b95c13116e37cf2c9c8ecb02a31f1127b6c7bc6b5c7cad054961
+size 1263148201