Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 40,
+  "<s>": 39
+}

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 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "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]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,41 @@
+{
+  "[PAD]": 0,
+  "[UNK]": 38,
+  "|": 29,
+  "ህ": 3,
+  "ል": 19,
+  "ም": 30,
+  "ር": 18,
+  "ስ": 17,
+  "ሽ": 36,
+  "ቅ": 35,
+  "ብ": 28,
+  "ቭ": 10,
+  "ት": 23,
+  "ች": 32,
+  "ን": 24,
+  "ኝ": 4,
+  "ኡ": 12,
+  "ኢ": 34,
+  "ኣ": 9,
+  "ኤ": 20,
+  "እ": 22,
+  "ኦ": 5,
+  "ኧ": 11,
+  "ክ": 16,
+  "ኰ": 26,
+  "ኸ": 8,
+  "ው": 6,
+  "ዝ": 15,
+  "ዥ": 2,
+  "ይ": 33,
+  "ድ": 21,
+  "ጅ": 13,
+  "ግ": 14,
+  "ጥ": 7,
+  "ጭ": 31,
+  "ጵ": 27,
+  "ጽ": 25,
+  "ፍ": 37,
+  "ፕ": 1
+}