Chahat7874
/

hindi_turkish

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Chahat7874 commited on Jun 17

Commit

a18d6ea

•

1 Parent(s): a790c4e

Upload tokenizer

Files changed (4) hide show

README.md +1 -1
added_tokens.json +2 -2
tokenizer_config.json +4 -4
vocab.json +38 -35

README.md CHANGED Viewed

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
 model-index:
 - name: wav2vec2-large-xls-r-300m-hindi_telugu-colab
   results: []

 ---
 license: apache-2.0
 tags:
 - generated_from_trainer
+base_model: facebook/wav2vec2-xls-r-300m
 model-index:
 - name: wav2vec2-large-xls-r-300m-hindi_telugu-colab
   results: []

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 66,
-  "<s>": 65
 }

 {
+  "</s>": 69,
+  "<s>": 68
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "63": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "64": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "65": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "66": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

 {
   "added_tokens_decoder": {
+    "66": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "67": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "68": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "69": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
-  "[PAD]": 64,
-  "[UNK]": 63,
   "|": 0,
   "ं": 1,
   "अ": 2,
@@ -29,39 +29,42 @@
   "श": 25,
   "ष": 26,
   "स": 27,
-  "ह": 28,
-  "़": 29,
-  "ा": 30,
-  "ि": 31,
-  "ी": 32,
-  "ु": 33,
-  "ू": 34,
-  "े": 35,
-  "ै": 36,
-  "ॉ": 37,
-  "ो": 38,
-  "्": 39,
-  "ం": 40,
   "ఎ": 41,
   "క": 42,
-  "చ": 43,
-  "ట": 44,
-  "డ": 45,
-  "త": 46,
-  "ద": 47,
-  "న": 48,
-  "ప": 49,
-  "మ": 50,
-  "ర": 51,
-  "ల": 52,
-  "వ": 53,
-  "శ": 54,
-  "ష": 55,
-  "ా": 56,
-  "ి": 57,
-  "ు": 58,
-  "ే": 59,
-  "ొ": 60,
-  "ో": 61,
-  "్": 62
 }

 {
+  "[PAD]": 67,
+  "[UNK]": 66,
   "|": 0,
   "ं": 1,
   "अ": 2,
   "श": 25,
   "ष": 26,
   "स": 27,
+  "़": 28,
+  "ा": 29,
+  "ि": 30,
+  "ी": 31,
+  "ु": 32,
+  "ू": 33,
+  "े": 34,
+  "ै": 35,
+  "ॉ": 36,
+  "ो": 37,
+  "्": 38,
+  "ం": 39,
+  "అ": 40,
   "ఎ": 41,
   "క": 42,
+  "గ": 43,
+  "చ": 44,
+  "ట": 45,
+  "డ": 46,
+  "త": 47,
+  "ద": 48,
+  "న": 49,
+  "ప": 50,
+  "బ": 51,
+  "మ": 52,
+  "ర": 53,
+  "ల": 54,
+  "వ": 55,
+  "శ": 56,
+  "ష": 57,
+  "స": 58,
+  "ా": 59,
+  "ి": 60,
+  "ు": 61,
+  "ే": 62,
+  "ొ": 63,
+  "ో": 64,
+  "్": 65
 }