Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
-library_name: transformers
 base_model: Harveenchadha/vakyansh-wav2vec2-nepali-nem-130
-tags:
-- generated_from_trainer
+library_name: transformers
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: indic-nepali-finetune-colab-test
   results: []

added_tokens.json

@@ -1,6 +1,6 @@
 {
-  "</s>": 67,
-  "<s>": 66,
-  "[PAD]": 65,
-  "[UNK]": 64
+  "</s>": 61,
+  "<s>": 60,
+  "[PAD]": 59,
+  "[UNK]": 58
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "64": {
+    "58": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "65": {
+    "59": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "66": {
+    "60": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "67": {
+    "61": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,6 +1,6 @@
 {
-  "[PAD]": 65,
-  "[UNK]": 64,
+  "[PAD]": 59,
+  "[UNK]": 58,
   "ँ": 1,
   "ं": 2,
   "अ": 3,
@@ -8,61 +8,55 @@
   "इ": 5,
   "ई": 6,
   "उ": 7,
-  "ऋ": 8,
-  "ए": 9,
-  "ऐ": 10,
-  "ओ": 11,
-  "औ": 12,
-  "क": 13,
-  "ख": 14,
-  "ग": 15,
-  "घ": 16,
-  "ङ": 17,
-  "च": 18,
-  "छ": 19,
-  "ज": 20,
-  "झ": 21,
-  "ञ": 22,
-  "ट": 23,
-  "ठ": 24,
-  "ड": 25,
-  "ढ": 26,
-  "ण": 27,
-  "त": 28,
-  "थ": 29,
-  "द": 30,
-  "ध": 31,
-  "न": 32,
-  "प": 33,
-  "फ": 34,
-  "ब": 35,
-  "भ": 36,
-  "म": 37,
-  "य": 38,
-  "र": 39,
-  "ल": 40,
-  "व": 41,
-  "श": 42,
-  "ष": 43,
-  "स": 44,
-  "ह": 45,
-  "ा": 46,
-  "ि": 47,
-  "ी": 48,
-  "ु": 49,
-  "ू": 50,
-  "ृ": 51,
-  "ै": 53,
-  "ो": 54,
-  "ौ": 55,
-  "०": 58,
-  "१": 59,
-  "२": 60,
-  "३": 61,
-  "४": 62,
-  "५": 63,
-  "६": 64,
-  "७": 65,
-  "८": 66,
-  "९": 67
+  "ए": 8,
+  "ओ": 9,
+  "औ": 10,
+  "क": 11,
+  "ख": 12,
+  "ग": 13,
+  "घ": 14,
+  "ङ": 15,
+  "च": 16,
+  "छ": 17,
+  "ज": 18,
+  "ञ": 19,
+  "ट": 20,
+  "ठ": 21,
+  "ड": 22,
+  "ण": 23,
+  "त": 24,
+  "थ": 25,
+  "द": 26,
+  "ध": 27,
+  "न": 28,
+  "प": 29,
+  "फ": 30,
+  "ब": 31,
+  "भ": 32,
+  "म": 33,
+  "य": 34,
+  "र": 35,
+  "ल": 36,
+  "व": 37,
+  "श": 38,
+  "ष": 39,
+  "स": 40,
+  "ह": 41,
+  "ा": 42,
+  "ि": 43,
+  "ी": 44,
+  "ु": 45,
+  "ू": 46,
+  "ो": 48,
+  "ौ": 49,
+  "०": 52,
+  "१": 53,
+  "२": 54,
+  "३": 55,
+  "४": 56,
+  "५": 57,
+  "६": 58,
+  "७": 59,
+  "८": 60,
+  "९": 61
 }