Upload lm-boosted decoder

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", " ", "\u1295", "\u1260", "\u1275", "\u12e8", "\u12cd", "\u1235", "\u122d", "\u1218", "\u120d", "\u121d", "\u127d", "\u12ed", "\u12a0", "\u1208", "\u1270", "\u12a5", "\u1290", "\u12eb", "\u1293", "\u120b", "\u12a8", "\u12f0", "\u12f5", "\u1265", "\u121b", "\u1228", "\u130d", "\u1308", "\u12c8", "\u1273", "\u122b", "\u1230", "\u1325", "\u121a", "\u12ad", "\u1263", "\u12ce", "\u1240", "\u1209", "\u122a", "\u1320", "\u12ab", "\u1233", "\u1206", "\u134d", "\u1245", "\u1205", "\u12f3", "\u12cb", "\u130b", "\u1278", "\u1276", "\u129b", "\u122e", "\u1323", "\u1348", "\u120a", "\u120e", "\u1201", "0", "\u1229", "\u1271", "\u1243", "\u12dd", "\u1296", "\u1232", "\u12d8", "\u1262", "\u1363", "\u12ca", "\u12f2", "\u130a", "1", "\u1309", "\u121e", "\u1266", "\u12dc", "\u120c", "\u1291", "\u12db", "\u1300", "\u123d", "\u12d9", "\u12ae", "\u121c", "\u12d3", "\u12da", "\u1261", "\u134a", "\u12f6", "\u1203", "\u130e", "\u1264", "\u127b", "\u1292", "\u12e9", "\u12d5", "\u1328", "\u1279", "2", "\u1241", "\u134b", "\u1246", "\u12f1", "\u1305", "\u12aa", "\u122c", "\u1231", "a", "\u1272", "\u12a4", "\u124b", "\u1219", "\u1294", "\u1236", "\u1353", "\u123b", "\u1355", "\u1200", "\u129d", "\u1356", "\u12a2", "\u132b", "\u12ee", "\u1274", "\u1215", "\u132d", "\u1225", "\u1303", "\u1234", "o", "\u12a9", "\u1204", ".", "9", "\u1313", "n", "-", "\u12a6", "5", "\u1238", "e", "\u1242", "\u134e", "4", "\u128b", "\u1321", "i", "3", "\u1298", "\u1352", "\u133d", "6", "r", "8", "t", "\u1349", "\u1326", "\u1299", "s", "l", "\u1302", "\u12de", "\u126a", "\u1277", "\u1345", "\u1306", "\u1283", "c", "\u1220", "u", "\u12ac", "\u12f4", "\u1343", "\u129e", "7", "\u12b3", "m", "p", "\u1202", "\u120f", "h", "\u1340", "\u1362", "\u1210", "\u126b", "\u1338", "\u123a", "\u1324", ",", "\u134c", "\u122f", "g", "\u1361", "\u133b", "\u12cc", "\u12e5", "\u1301", "d", "\u1350", "b", "\u1268", "\u1239", "/", "\u123e", "\u1267", "\u126c", "\u121f", "\u126d", "\u201d", "\u1354", "\u132a", "k", "f", "\u1244", "\u127a", "y", "\u134f", "\u1237", "\u1304", "\u12ec", "w", "v", "\u1223", "\u1226", "\u130c", "\u12e3", "\u127e", "\u1214", "\u1329", "\u1211", "\u1327", "\u1297", "j", "\u132e", "\u12d0", "\u127c", "\"", ":", "\u129a", "\u12e6", "\u12f7", "\u1364", "\u12e2", "\u12d1", "\u12c9", "\u1285", "\u12a3", "\u1346", "\u133e", "x", "$", "\u12a1", "\u1322", "\u126e", "\u00ab", "\u00bb", "\u1351", "\u1339", "%", "\u12df", "z", "\u12e1", "\u1335", "\u2014", "\u1341", "\u133f", "\u12ea", "?", "\u2019", "\u123c", "+", "\u1365", "\u12d2", "\u00b0", "\u123f", "\u12d6", "\u1310", "\u00f5", "\u2013", "\u12b8", ";", "\u00e3", "\u00a5", "\u12ba", "\u1334", "\u1333", "\u129c", "'", "\u1307", "\u133a", "\u2018", "!", "\u00b2", "\u127f", "\u12b0", "\u1357", "q", "&", "\u00a3", "\u129f", "[", "]", "\u1366", "\u1280", "\u1248", "\u1312", "\u12b5", "\u1213", "\u124d", "\u124a", "\u1221", "\u1332", "\u1336", "\u12b9", "\u12be", "\u1224", "\u1315", "\u12bd", "\u12bb", "\u12d4", "\u132c", "\u133c", "\u1284", "\u12e4", "\u1286", "\u1216", "\u12e0", "\u132f", "\u1331", "\u1330", "\u1222", "\u1344", "\u1212"], "is_bpe": false}

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/output_allVocab.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c6753ec5baa7008de6eb39a94c6ce44771617b09df2df20dc6842f245e552b
+size 368790803

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28398083a30d050bee55167294c69024ef692657626ae82cb9a71e556e726082
+size 26398784

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,341 @@
+{
+  "!": 297,
+  "\"": 242,
+  "$": 256,
+  "%": 264,
+  "&": 303,
+  "'": 293,
+  "+": 276,
+  ",": 194,
+  "-": 142,
+  ".": 138,
+  "/": 208,
+  "0": 64,
+  "1": 77,
+  "2": 104,
+  "3": 153,
+  "4": 149,
+  "5": 144,
+  "6": 157,
+  "7": 180,
+  "8": 159,
+  "9": 139,
+  ":": 243,
+  ";": 286,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "?": 273,
+  "[": 306,
+  "]": 307,
+  "a": 113,
+  "b": 205,
+  "c": 173,
+  "d": 203,
+  "e": 146,
+  "f": 218,
+  "g": 197,
+  "h": 186,
+  "i": 152,
+  "j": 238,
+  "k": 217,
+  "l": 165,
+  "m": 182,
+  "n": 141,
+  "o": 135,
+  "p": 183,
+  "q": 302,
+  "r": 158,
+  "s": 164,
+  "t": 160,
+  "u": 175,
+  "v": 227,
+  "w": 226,
+  "x": 255,
+  "y": 221,
+  "z": 266,
+  "|": 4,
+  "£": 304,
+  "¥": 288,
+  "«": 260,
+  "°": 279,
+  "²": 298,
+  "»": 261,
+  "ã": 287,
+  "õ": 283,
+  "ሀ": 123,
+  "ሁ": 63,
+  "ሂ": 184,
+  "ሃ": 95,
+  "ሄ": 137,
+  "ህ": 51,
+  "ሆ": 48,
+  "ለ": 18,
+  "ሉ": 43,
+  "ሊ": 61,
+  "ላ": 24,
+  "ሌ": 82,
+  "ል": 13,
+  "ሎ": 62,
+  "ሏ": 185,
+  "ሐ": 189,
+  "ሑ": 235,
+  "ሒ": 338,
+  "ሓ": 313,
+  "ሔ": 233,
+  "ሕ": 130,
+  "ሖ": 331,
+  "መ": 12,
+  "ሙ": 117,
+  "ሚ": 38,
+  "ማ": 29,
+  "ሜ": 89,
+  "ም": 14,
+  "ሞ": 79,
+  "ሟ": 212,
+  "ሠ": 174,
+  "ሡ": 316,
+  "ሢ": 336,
+  "ሣ": 228,
+  "ሤ": 321,
+  "ሥ": 132,
+  "ሦ": 229,
+  "ረ": 30,
+  "ሩ": 65,
+  "ሪ": 44,
+  "ራ": 35,
+  "ሬ": 111,
+  "ር": 11,
+  "ሮ": 58,
+  "ሯ": 196,
+  "ሰ": 36,
+  "ሱ": 112,
+  "ሲ": 70,
+  "ሳ": 47,
+  "ሴ": 134,
+  "ስ": 10,
+  "ሶ": 119,
+  "ሷ": 223,
+  "ሸ": 145,
+  "ሹ": 207,
+  "ሺ": 192,
+  "ሻ": 121,
+  "ሼ": 275,
+  "ሽ": 86,
+  "ሾ": 209,
+  "ሿ": 280,
+  "ቀ": 42,
+  "ቁ": 105,
+  "ቂ": 147,
+  "ቃ": 67,
+  "ቄ": 219,
+  "ቅ": 50,
+  "ቆ": 107,
+  "ቈ": 310,
+  "ቊ": 315,
+  "ቋ": 116,
+  "ቍ": 314,
+  "በ": 6,
+  "ቡ": 92,
+  "ቢ": 72,
+  "ባ": 40,
+  "ቤ": 97,
+  "ብ": 28,
+  "ቦ": 80,
+  "ቧ": 210,
+  "ቨ": 206,
+  "ቪ": 168,
+  "ቫ": 190,
+  "ቬ": 211,
+  "ቭ": 213,
+  "ቮ": 259,
+  "ተ": 19,
+  "ቱ": 66,
+  "ቲ": 114,
+  "ታ": 34,
+  "ቴ": 129,
+  "ት": 7,
+  "ቶ": 56,
+  "ቷ": 169,
+  "ቸ": 55,
+  "ቹ": 103,
+  "ቺ": 220,
+  "ቻ": 98,
+  "ቼ": 241,
+  "ች": 15,
+  "ቾ": 232,
+  "ቿ": 299,
+  "ኀ": 309,
+  "ኃ": 172,
+  "ኄ": 328,
+  "ኅ": 251,
+  "ኆ": 330,
+  "ኋ": 150,
+  "ነ": 21,
+  "ኑ": 83,
+  "ኒ": 99,
+  "ና": 23,
+  "ኔ": 118,
+  "ን": 5,
+  "ኖ": 69,
+  "ኗ": 237,
+  "ኘ": 154,
+  "ኙ": 163,
+  "ኚ": 244,
+  "ኛ": 57,
+  "ኜ": 292,
+  "ኝ": 124,
+  "ኞ": 179,
+  "ኟ": 305,
+  "አ": 17,
+  "ኡ": 257,
+  "ኢ": 126,
+  "ኣ": 252,
+  "ኤ": 115,
+  "እ": 20,
+  "ኦ": 143,
+  "ከ": 25,
+  "ኩ": 136,
+  "ኪ": 110,
+  "ካ": 46,
+  "ኬ": 176,
+  "ክ": 39,
+  "ኮ": 88,
+  "ኰ": 300,
+  "ኳ": 181,
+  "ኵ": 312,
+  "ኸ": 285,
+  "ኹ": 319,
+  "ኺ": 289,
+  "ኻ": 324,
+  "ኽ": 323,
+  "ኾ": 320,
+  "ወ": 33,
+  "ዉ": 250,
+  "ዊ": 74,
+  "ዋ": 53,
+  "ዌ": 200,
+  "ው": 9,
+  "ዎ": 41,
+  "ዐ": 240,
+  "ዑ": 249,
+  "ዒ": 278,
+  "ዓ": 90,
+  "ዔ": 325,
+  "ዕ": 101,
+  "ዖ": 281,
+  "ዘ": 71,
+  "ዙ": 87,
+  "ዚ": 91,
+  "ዛ": 84,
+  "ዜ": 81,
+  "ዝ": 68,
+  "ዞ": 167,
+  "ዟ": 265,
+  "ዠ": 332,
+  "ዡ": 267,
+  "ዢ": 248,
+  "ዣ": 231,
+  "ዤ": 329,
+  "ዥ": 201,
+  "ዦ": 245,
+  "የ": 8,
+  "ዩ": 100,
+  "ዪ": 272,
+  "ያ": 22,
+  "ዬ": 225,
+  "ይ": 16,
+  "ዮ": 128,
+  "ደ": 26,
+  "ዱ": 108,
+  "ዲ": 75,
+  "ዳ": 52,
+  "ዴ": 177,
+  "ድ": 27,
+  "ዶ": 94,
+  "ዷ": 246,
+  "ጀ": 85,
+  "ጁ": 202,
+  "ጂ": 166,
+  "ጃ": 133,
+  "ጄ": 224,
+  "ጅ": 109,
+  "ጆ": 171,
+  "ጇ": 294,
+  "ገ": 32,
+  "ጉ": 78,
+  "ጊ": 76,
+  "ጋ": 54,
+  "ጌ": 230,
+  "ግ": 31,
+  "ጎ": 96,
+  "ጐ": 282,
+  "ጒ": 311,
+  "ጓ": 140,
+  "ጕ": 322,
+  "ጠ": 45,
+  "ጡ": 151,
+  "ጢ": 258,
+  "ጣ": 59,
+  "ጤ": 193,
+  "ጥ": 37,
+  "ጦ": 162,
+  "ጧ": 236,
+  "ጨ": 102,
+  "ጩ": 234,
+  "ጪ": 216,
+  "ጫ": 127,
+  "ጬ": 326,
+  "ጭ": 131,
+  "ጮ": 239,
+  "ጯ": 333,
+  "ጰ": 335,
+  "ጱ": 334,
+  "ጲ": 317,
+  "ጳ": 291,
+  "ጴ": 290,
+  "ጵ": 268,
+  "ጶ": 318,
+  "ጸ": 191,
+  "ጹ": 263,
+  "ጺ": 295,
+  "ጻ": 199,
+  "ጼ": 327,
+  "ጽ": 156,
+  "ጾ": 254,
+  "ጿ": 271,
+  "ፀ": 187,
+  "ፁ": 270,
+  "ፃ": 178,
+  "ፄ": 337,
+  "ፅ": 170,
+  "ፆ": 253,
+  "ፈ": 60,
+  "ፉ": 161,
+  "ፊ": 93,
+  "ፋ": 106,
+  "ፌ": 195,
+  "ፍ": 49,
+  "ፎ": 148,
+  "ፏ": 222,
+  "ፐ": 204,
+  "ፑ": 262,
+  "ፒ": 155,
+  "ፓ": 120,
+  "ፔ": 215,
+  "ፕ": 122,
+  "ፖ": 125,
+  "ፗ": 301,
+  "፡": 198,
+  "።": 188,
+  "፣": 73,
+  "፤": 247,
+  "፥": 277,
+  "፦": 308,
+  "–": 284,
+  "—": 269,
+  "‘": 296,
+  "’": 274,
+  "”": 214
+}