Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: cc-by-nc-4.0
-base_model: facebook/mms-1b-all
 tags:
 - generated_from_trainer
+base_model: facebook/mms-1b-all
 datasets:
 - common_voice_16_1
 model-index:

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 43,
+  "<s>": 42
+}

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": {
+    "40": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "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]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "swh",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,46 @@
+{
+  "swh": {
+    "/": 1,
+    "[PAD]": 41,
+    "[UNK]": 40,
+    "\\": 2,
+    "a": 3,
+    "b": 4,
+    "c": 5,
+    "d": 6,
+    "e": 7,
+    "f": 8,
+    "g": 9,
+    "h": 10,
+    "i": 11,
+    "j": 12,
+    "k": 13,
+    "l": 14,
+    "m": 15,
+    "n": 16,
+    "o": 17,
+    "p": 18,
+    "q": 19,
+    "r": 20,
+    "s": 21,
+    "t": 22,
+    "u": 23,
+    "v": 24,
+    "w": 25,
+    "x": 26,
+    "y": 27,
+    "z": 28,
+    "|": 0,
+    "°": 29,
+    "à": 30,
+    "á": 31,
+    "å": 32,
+    "è": 33,
+    "é": 34,
+    "ó": 35,
+    "š": 36,
+    "ū": 37,
+    "–": 38,
+    "’": 39
+  }
+}