Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
+base_model: facebook/wav2vec2-xls-r-300m
 datasets:
 - common_voice_11_0
 metrics:
@@ -11,8 +11,8 @@ model-index:
 - name: wav2vec2-large-xls-r-300m-assamese_speech_to_IPA
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_11_0
       type: common_voice_11_0
@@ -20,9 +20,9 @@ model-index:
       split: test
       args: as
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.5796
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 43,
-  "<s>": 42
+  "</s>": 51,
+  "<s>": 50
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "40": {
+    "48": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "41": {
+    "49": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "42": {
+    "50": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "43": {
+    "51": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,44 +1,52 @@
 {
-  ".": 1,
-  "/": 2,
-  "[PAD]": 41,
-  "[UNK]": 40,
-  "a": 3,
-  "b": 4,
-  "d": 5,
-  "e": 6,
-  "g": 7,
-  "h": 8,
-  "i": 9,
-  "j": 10,
-  "k": 11,
-  "l": 12,
-  "m": 13,
-  "n": 14,
-  "o": 15,
-  "p": 16,
-  "t": 17,
-  "u": 18,
-  "x": 19,
+  "!": 1,
+  "\"": 2,
+  "'": 3,
+  ",": 4,
+  "-": 5,
+  ".": 6,
+  "?": 7,
+  "[PAD]": 49,
+  "[UNK]": 48,
+  "a": 8,
+  "b": 9,
+  "d": 10,
+  "e": 11,
+  "g": 12,
+  "h": 13,
+  "i": 14,
+  "j": 15,
+  "k": 16,
+  "l": 17,
+  "m": 18,
+  "n": 19,
+  "o": 20,
+  "p": 21,
+  "t": 22,
+  "u": 23,
+  "x": 24,
   "|": 0,
-  "ŋ": 20,
-  "ɒ": 21,
-  "ɔ": 22,
-  "ɡ": 23,
-  "ɪ": 24,
-  "ɲ": 25,
-  "ɹ": 26,
-  "ʃ": 27,
-  "ʊ": 28,
-  "ʤ": 29,
-  "ʰ": 30,
-  "ʱ": 31,
-  "ˑ": 32,
-  "̃": 33,
-  "়": 34,
-  "ূ": 35,
-  "ৃ": 36,
-  "৷": 37,
-  "ṱ": 38,
-  "’": 39
+  "ŋ": 25,
+  "ɒ": 26,
+  "ɔ": 27,
+  "ɡ": 28,
+  "ɪ": 29,
+  "ɲ": 30,
+  "ɹ": 31,
+  "ʃ": 32,
+  "ʊ": 33,
+  "ʤ": 34,
+  "ʰ": 35,
+  "ʱ": 36,
+  "ˑ": 37,
+  "̃": 38,
+  "়": 39,
+  "ৃ": 40,
+  "্": 41,
+  "৷": 42,
+  "ṱ": 43,
+  "‘": 44,
+  "’": 45,
+  "“": 46,
+  "”": 47
 }