Upload processor

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 128,
+  "<s>": 127
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

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 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "125": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,129 @@
+{
+  "[PAD]": 126,
+  "[UNK]": 125,
+  "|": 86,
+  "ༀ": 22,
+  "༆": 55,
+  "་": 14,
+  "༌": 99,
+  "།": 74,
+  "༎": 87,
+  "༔": 79,
+  "༕": 116,
+  "༜": 57,
+  "༡": 44,
+  "༢": 24,
+  "༣": 85,
+  "༤": 93,
+  "༥": 52,
+  "༦": 102,
+  "༧": 23,
+  "༨": 2,
+  "༩": 111,
+  "༰": 96,
+  "༷": 15,
+  "༸": 118,
+  "༾": 16,
+  "ཀ": 53,
+  "ཁ": 64,
+  "ག": 119,
+  "གྷ": 81,
+  "ང": 0,
+  "ཅ": 39,
+  "ཆ": 26,
+  "ཇ": 59,
+  "ཉ": 67,
+  "ཊ": 97,
+  "ཋ": 11,
+  "ཌ": 5,
+  "ཌྷ": 72,
+  "ཎ": 108,
+  "ཏ": 121,
+  "ཐ": 60,
+  "ད": 6,
+  "དྷ": 9,
+  "ན": 4,
+  "པ": 63,
+  "ཕ": 92,
+  "བ": 115,
+  "བྷ": 38,
+  "མ": 47,
+  "ཙ": 48,
+  "ཚ": 106,
+  "ཛ": 25,
+  "ཛྷ": 56,
+  "ཝ": 37,
+  "ཞ": 84,
+  "ཟ": 19,
+  "འ": 94,
+  "ཡ": 28,
+  "ར": 112,
+  "ལ": 103,
+  "ཤ": 70,
+  "ཥ": 34,
+  "ས": 21,
+  "ཧ": 107,
+  "ཨ": 45,
+  "ཀྵ": 50,
+  "ཪ": 71,
+  "ཱ": 76,
+  "ི": 49,
+  "ཱི": 78,
+  "ུ": 20,
+  "ཱུ": 91,
+  "ཷ": 65,
+  "ེ": 1,
+  "ཻ": 7,
+  "ོ": 75,
+  "ཽ": 82,
+  "ཾ": 27,
+  "ཿ": 61,
+  "ྀ": 51,
+  "ཱྀ": 124,
+  "ྂ": 66,
+  "ྃ": 62,
+  "྄": 31,
+  "྅": 17,
+  "྆": 105,
+  "྇": 100,
+  "ྋ": 46,
+  "ྐ": 117,
+  "ྑ": 35,
+  "ྒ": 33,
+  "ྔ": 40,
+  "ྕ": 123,
+  "ྖ": 89,
+  "ྗ": 42,
+  "ྙ": 8,
+  "ྚ": 69,
+  "ྛ": 30,
+  "ྜ": 104,
+  "ྞ": 113,
+  "ྟ": 90,
+  "ྠ": 41,
+  "ྡ": 77,
+  "ྡྷ": 101,
+  "ྣ": 120,
+  "ྤ": 95,
+  "ྥ": 18,
+  "ྦ": 10,
+  "ྦྷ": 58,
+  "ྨ": 12,
+  "ྩ": 83,
+  "ྪ": 110,
+  "ྫ": 29,
+  "ྭ": 98,
+  "ྰ": 36,
+  "ྱ": 32,
+  "ྲ": 114,
+  "ླ": 109,
+  "ྴ": 80,
+  "ྵ": 122,
+  "ྶ": 54,
+  "ྷ": 13,
+  "ྻ": 88,
+  "ྼ": 68,
+  "࿌": 3,
+  "࿒": 43,
+  "​": 73
+}