Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
 license: cc-by-nc-4.0
-base_model: facebook/mms-1b-all
 tags:
 - generated_from_trainer
 datasets:
 - common_voice_16_0
+base_model: facebook/mms-1b-all
 model-index:
 - name: runs
   results: []

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 44,
+  "<mask>": 45,
+  "<s>": 43
+}

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "<mask>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "41": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "<mask>",
+      "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>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "hy",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,47 @@
+{
+  "hy": {
+    "-": 1,
+    "[PAD]": 42,
+    "[UNK]": 41,
+    "|": 0,
+    "ա": 2,
+    "բ": 3,
+    "գ": 4,
+    "դ": 5,
+    "ե": 6,
+    "զ": 7,
+    "է": 8,
+    "ը": 9,
+    "թ": 10,
+    "ժ": 11,
+    "ի": 12,
+    "լ": 13,
+    "խ": 14,
+    "ծ": 15,
+    "կ": 16,
+    "հ": 17,
+    "ձ": 18,
+    "ղ": 19,
+    "ճ": 20,
+    "մ": 21,
+    "յ": 22,
+    "ն": 23,
+    "շ": 24,
+    "ո": 25,
+    "չ": 26,
+    "պ": 27,
+    "ջ": 28,
+    "ռ": 29,
+    "ս": 30,
+    "վ": 31,
+    "տ": 32,
+    "ր": 33,
+    "ց": 34,
+    "ւ": 35,
+    "փ": 36,
+    "ք": 37,
+    "օ": 38,
+    "ֆ": 39,
+    "և": 40
+  }
+}