Sajjo
/

wav2vec2-large-mms-1b-tamil-v1

Transformers

Inference Endpoints

Model card Files Files and versions Community

Sajjo commited on May 7

Commit

8c98af7

•

1 Parent(s): 17c6f1a

Upload tokenizer

Browse files

Files changed (3) hide show

added_tokens.json +2 -2
tokenizer_config.json +5 -5
vocab.json +86 -100

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 101,
-  "<s>": 100
 }

 {
+  "</s>": 87,
+  "<s>": 86
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "98": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "99": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "100": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "101": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,7 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
-  "target_lang": "tur",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

 {
   "added_tokens_decoder": {
+    "84": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "85": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "86": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "87": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
+  "target_lang": "ta",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

vocab.json CHANGED Viewed

@@ -1,104 +1,90 @@
 {
-  "tur": {
-    "&": 1,
-    "(": 2,
-    ")": 3,
-    "[PAD]": 99,
-    "[UNK]": 98,
-    "\\": 4,
-    "_": 5,
-    "`": 6,
-    "a": 7,
-    "b": 8,
-    "c": 9,
-    "d": 10,
-    "e": 11,
-    "f": 12,
-    "g": 13,
-    "h": 14,
-    "i": 15,
-    "j": 16,
-    "k": 17,
-    "l": 18,
-    "m": 19,
-    "n": 20,
-    "o": 21,
-    "p": 22,
-    "q": 23,
-    "r": 24,
-    "s": 25,
-    "t": 26,
-    "u": 27,
-    "v": 28,
-    "w": 29,
-    "x": 30,
-    "y": 31,
-    "z": 32,
     "|": 0,
-    "·": 33,
-    "½": 34,
-    "¾": 35,
-    "á": 36,
-    "é": 37,
-    "š": 38,
-    "ஃ": 39,
-    "அ": 40,
-    "ஆ": 41,
-    "இ": 42,
-    "ஈ": 43,
-    "உ": 44,
-    "ஊ": 45,
-    "எ": 46,
-    "ஏ": 47,
-    "ஐ": 48,
-    "ஒ": 49,
-    "ஓ": 50,
-    "ஔ": 51,
-    "க": 52,
-    "ங": 53,
-    "ச": 54,
-    "ஜ": 55,
-    "ஞ": 56,
-    "ட": 57,
-    "ண": 58,
-    "த": 59,
-    "ந": 60,
-    "ன": 61,
-    "ப": 62,
-    "ம": 63,
-    "ய": 64,
-    "ர": 65,
-    "ற": 66,
-    "ல": 67,
-    "ள": 68,
-    "ழ": 69,
-    "வ": 70,
-    "ஷ": 71,
-    "ஸ": 72,
-    "ஹ": 73,
-    "ா": 74,
-    "ி": 75,
-    "ீ": 76,
-    "ு": 77,
-    "ூ": 78,
-    "ெ": 79,
-    "ே": 80,
-    "ை": 81,
-    "ொ": 82,
-    "ோ": 83,
-    "ௌ": 84,
-    "்": 85,
-    "ௗ": 86,
-    "ഥ": 87,
-    "–": 88,
-    "—": 89,
-    "’": 90,
-    "‚": 91,
-    "•": 92,
-    "…": 93,
-    "′": 94,
-    "″": 95,
-    "●": 96,
-    "◯": 97
   }
 }

 {
+  "ta": {
+    "[PAD]": 85,
+    "[UNK]": 84,
+    "\\": 1,
+    "a": 2,
+    "b": 3,
+    "c": 4,
+    "d": 5,
+    "e": 6,
+    "f": 7,
+    "g": 8,
+    "h": 9,
+    "i": 10,
+    "j": 11,
+    "k": 12,
+    "l": 13,
+    "m": 14,
+    "n": 15,
+    "o": 16,
+    "p": 17,
+    "q": 18,
+    "r": 19,
+    "s": 20,
+    "t": 21,
+    "u": 22,
+    "v": 23,
+    "w": 24,
+    "x": 25,
+    "y": 26,
+    "z": 27,
     "|": 0,
+    "½": 28,
+    "¾": 29,
+    "á": 30,
+    "é": 31,
+    "š": 32,
+    "அ": 33,
+    "ஆ": 34,
+    "இ": 35,
+    "ஈ": 36,
+    "உ": 37,
+    "ஊ": 38,
+    "எ": 39,
+    "ஏ": 40,
+    "ஐ": 41,
+    "ஒ": 42,
+    "ஓ": 43,
+    "ஔ": 44,
+    "க": 45,
+    "ங": 46,
+    "ச": 47,
+    "ஜ": 48,
+    "ஞ": 49,
+    "ட": 50,
+    "ண": 51,
+    "த": 52,
+    "ந": 53,
+    "ன": 54,
+    "ப": 55,
+    "ம": 56,
+    "ய": 57,
+    "ர": 58,
+    "ற": 59,
+    "ல": 60,
+    "ள": 61,
+    "ழ": 62,
+    "வ": 63,
+    "ஷ": 64,
+    "ஸ": 65,
+    "ஹ": 66,
+    "ா": 67,
+    "ி": 68,
+    "ீ": 69,
+    "ு": 70,
+    "ூ": 71,
+    "ெ": 72,
+    "ே": 73,
+    "ை": 74,
+    "ொ": 75,
+    "ோ": 76,
+    "ௌ": 77,
+    "்": 78,
+    "ௗ": 79,
+    "ഥ": 80,
+    "–": 81,
+    "●": 82,
+    "◯": 83
   }
 }