Upload processor

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 252,
+  "<s>": 251
+}

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "249": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "250": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "251": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "252": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2BertProcessor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,253 @@
+{
+  "0": 1,
+  "1": 2,
+  "2": 3,
+  "3": 4,
+  "4": 5,
+  "5": 6,
+  "6": 7,
+  "7": 8,
+  "8": 9,
+  "9": 10,
+  "[PAD]": 250,
+  "[UNK]": 249,
+  "|": 0,
+  "ሀ": 11,
+  "ሁ": 12,
+  "ሂ": 13,
+  "ሃ": 14,
+  "ሄ": 15,
+  "ህ": 16,
+  "ሆ": 17,
+  "ለ": 18,
+  "ሉ": 19,
+  "ሊ": 20,
+  "ላ": 21,
+  "ሌ": 22,
+  "ል": 23,
+  "ሎ": 24,
+  "ሐ": 25,
+  "ሑ": 26,
+  "ሒ": 27,
+  "ሓ": 28,
+  "ሔ": 29,
+  "ሕ": 30,
+  "ሖ": 31,
+  "መ": 32,
+  "ሙ": 33,
+  "ሚ": 34,
+  "ማ": 35,
+  "ሜ": 36,
+  "ም": 37,
+  "ሞ": 38,
+  "ሠ": 39,
+  "ሣ": 40,
+  "ሥ": 41,
+  "ሦ": 42,
+  "ረ": 43,
+  "ሩ": 44,
+  "ሪ": 45,
+  "ራ": 46,
+  "ሬ": 47,
+  "ር": 48,
+  "ሮ": 49,
+  "ሰ": 50,
+  "ሱ": 51,
+  "ሲ": 52,
+  "ሳ": 53,
+  "ሴ": 54,
+  "ስ": 55,
+  "ሶ": 56,
+  "ሸ": 57,
+  "ሹ": 58,
+  "ሺ": 59,
+  "ሻ": 60,
+  "ሼ": 61,
+  "ሽ": 62,
+  "ሾ": 63,
+  "ቀ": 64,
+  "ቁ": 65,
+  "ቂ": 66,
+  "ቃ": 67,
+  "ቄ": 68,
+  "ቅ": 69,
+  "ቆ": 70,
+  "ቐ": 71,
+  "ቑ": 72,
+  "ቒ": 73,
+  "ቓ": 74,
+  "ቕ": 75,
+  "ቖ": 76,
+  "ቘ": 77,
+  "ቚ": 78,
+  "ቛ": 79,
+  "ቝ": 80,
+  "በ": 81,
+  "ቡ": 82,
+  "ቢ": 83,
+  "ባ": 84,
+  "ቤ": 85,
+  "ብ": 86,
+  "ቦ": 87,
+  "ቨ": 88,
+  "ቪ": 89,
+  "ቫ": 90,
+  "ቬ": 91,
+  "ቭ": 92,
+  "ቮ": 93,
+  "ተ": 94,
+  "ቱ": 95,
+  "ቲ": 96,
+  "ታ": 97,
+  "ቴ": 98,
+  "ት": 99,
+  "ቶ": 100,
+  "ቸ": 101,
+  "ቹ": 102,
+  "ቺ": 103,
+  "ቻ": 104,
+  "ቼ": 105,
+  "ች": 106,
+  "ቾ": 107,
+  "ኀ": 108,
+  "ነ": 109,
+  "ኑ": 110,
+  "ኒ": 111,
+  "ና": 112,
+  "ኔ": 113,
+  "ን": 114,
+  "ኖ": 115,
+  "ኘ": 116,
+  "ኛ": 117,
+  "ኝ": 118,
+  "አ": 119,
+  "ኡ": 120,
+  "ኢ": 121,
+  "ኣ": 122,
+  "ኤ": 123,
+  "እ": 124,
+  "ኦ": 125,
+  "ኧ": 126,
+  "ከ": 127,
+  "ኩ": 128,
+  "ኪ": 129,
+  "ካ": 130,
+  "ኬ": 131,
+  "ክ": 132,
+  "ኮ": 133,
+  "ኰ": 134,
+  "ኲ": 135,
+  "ኳ": 136,
+  "ኵ": 137,
+  "ኸ": 138,
+  "ኹ": 139,
+  "ኺ": 140,
+  "ኻ": 141,
+  "ኼ": 142,
+  "ኽ": 143,
+  "ኾ": 144,
+  "ዂ": 145,
+  "ዃ": 146,
+  "ዅ": 147,
+  "ወ": 148,
+  "ዉ": 149,
+  "ዊ": 150,
+  "ዋ": 151,
+  "ዌ": 152,
+  "ው": 153,
+  "ዎ": 154,
+  "ዐ": 155,
+  "ዑ": 156,
+  "ዒ": 157,
+  "ዓ": 158,
+  "ዔ": 159,
+  "ዕ": 160,
+  "ዖ": 161,
+  "ዘ": 162,
+  "ዙ": 163,
+  "ዚ": 164,
+  "ዛ": 165,
+  "ዜ": 166,
+  "ዝ": 167,
+  "ዞ": 168,
+  "የ": 169,
+  "ዩ": 170,
+  "ዪ": 171,
+  "ያ": 172,
+  "ዬ": 173,
+  "ይ": 174,
+  "ዮ": 175,
+  "ደ": 176,
+  "ዱ": 177,
+  "ዲ": 178,
+  "ዳ": 179,
+  "ዴ": 180,
+  "ድ": 181,
+  "ዶ": 182,
+  "ዸ": 183,
+  "ጀ": 184,
+  "ጁ": 185,
+  "ጂ": 186,
+  "ጃ": 187,
+  "ጄ": 188,
+  "ጅ": 189,
+  "ጆ": 190,
+  "ገ": 191,
+  "ጉ": 192,
+  "ጊ": 193,
+  "ጋ": 194,
+  "ጌ": 195,
+  "ግ": 196,
+  "ጎ": 197,
+  "ጐ": 198,
+  "ጒ": 199,
+  "ጓ": 200,
+  "ጠ": 201,
+  "ጡ": 202,
+  "ጢ": 203,
+  "ጣ": 204,
+  "ጤ": 205,
+  "ጥ": 206,
+  "ጦ": 207,
+  "ጨ": 208,
+  "ጩ": 209,
+  "ጪ": 210,
+  "ጫ": 211,
+  "ጬ": 212,
+  "ጭ": 213,
+  "ጮ": 214,
+  "ጰ": 215,
+  "ጱ": 216,
+  "ጲ": 217,
+  "ጳ": 218,
+  "ጴ": 219,
+  "ጵ": 220,
+  "ጸ": 221,
+  "ጹ": 222,
+  "ጺ": 223,
+  "ጻ": 224,
+  "ጼ": 225,
+  "ጽ": 226,
+  "ጾ": 227,
+  "ፀ": 228,
+  "ፁ": 229,
+  "ፂ": 230,
+  "ፃ": 231,
+  "ፄ": 232,
+  "ፅ": 233,
+  "ፆ": 234,
+  "ፈ": 235,
+  "ፉ": 236,
+  "ፊ": 237,
+  "ፋ": 238,
+  "ፌ": 239,
+  "ፍ": 240,
+  "ፎ": 241,
+  "ፐ": 242,
+  "ፑ": 243,
+  "ፒ": 244,
+  "ፓ": 245,
+  "ፔ": 246,
+  "ፕ": 247,
+  "ፖ": 248
+}