Upload tokenizer

added_tokens.json

@@ -1,108 +1,109 @@
 {
-  "<|af|>": 50326,
-  "<|am|>": 50333,
-  "<|ar|>": 50271,
-  "<|as|>": 50349,
-  "<|az|>": 50303,
-  "<|ba|>": 50354,
-  "<|be|>": 50329,
-  "<|bg|>": 50291,
-  "<|bn|>": 50301,
-  "<|bo|>": 50346,
-  "<|br|>": 50308,
-  "<|bs|>": 50314,
-  "<|ca|>": 50269,
-  "<|cs|>": 50282,
-  "<|cy|>": 50296,
-  "<|da|>": 50284,
-  "<|de|>": 50260,
-  "<|el|>": 50280,
-  "<|en|>": 50258,
-  "<|es|>": 50261,
-  "<|et|>": 50306,
-  "<|eu|>": 50309,
-  "<|fa|>": 50299,
-  "<|fi|>": 50276,
-  "<|fo|>": 50337,
-  "<|fr|>": 50264,
-  "<|gl|>": 50318,
-  "<|gu|>": 50332,
-  "<|haw|>": 50351,
-  "<|ha|>": 50353,
-  "<|hi|>": 50275,
-  "<|hr|>": 50290,
-  "<|ht|>": 50338,
-  "<|hu|>": 50285,
-  "<|hy|>": 50311,
-  "<|id|>": 50274,
-  "<|is|>": 50310,
-  "<|it|>": 50273,
-  "<|iw|>": 50278,
-  "<|ja|>": 50265,
-  "<|jw|>": 50355,
-  "<|ka|>": 50328,
-  "<|kk|>": 50315,
-  "<|km|>": 50322,
-  "<|kn|>": 50305,
-  "<|ko|>": 50263,
-  "<|la|>": 50293,
-  "<|lb|>": 50344,
-  "<|ln|>": 50352,
-  "<|lo|>": 50335,
-  "<|lt|>": 50292,
-  "<|lv|>": 50300,
-  "<|mg|>": 50348,
-  "<|mi|>": 50294,
-  "<|mk|>": 50307,
-  "<|ml|>": 50295,
-  "<|mn|>": 50313,
-  "<|mr|>": 50319,
-  "<|ms|>": 50281,
-  "<|mt|>": 50342,
-  "<|my|>": 50345,
-  "<|ne|>": 50312,
-  "<|nl|>": 50270,
-  "<|nn|>": 50341,
-  "<|nocaptions|>": 50361,
-  "<|notimestamps|>": 50362,
-  "<|no|>": 50287,
-  "<|oc|>": 50327,
-  "<|pa|>": 50320,
-  "<|pl|>": 50268,
-  "<|ps|>": 50339,
-  "<|pt|>": 50266,
-  "<|ro|>": 50283,
-  "<|ru|>": 50262,
-  "<|sa|>": 50343,
-  "<|sd|>": 50331,
-  "<|si|>": 50321,
-  "<|sk|>": 50297,
-  "<|sl|>": 50304,
-  "<|sn|>": 50323,
-  "<|so|>": 50325,
-  "<|sq|>": 50316,
-  "<|sr|>": 50302,
-  "<|startoflm|>": 50359,
-  "<|startofprev|>": 50360,
-  "<|startoftranscript|>": 50257,
-  "<|su|>": 50356,
-  "<|sv|>": 50272,
-  "<|sw|>": 50317,
-  "<|ta|>": 50286,
-  "<|te|>": 50298,
-  "<|tg|>": 50330,
-  "<|th|>": 50288,
-  "<|tk|>": 50340,
-  "<|tl|>": 50347,
-  "<|transcribe|>": 50358,
-  "<|translate|>": 50357,
-  "<|tr|>": 50267,
-  "<|tt|>": 50350,
-  "<|uk|>": 50279,
-  "<|ur|>": 50289,
-  "<|uz|>": 50336,
-  "<|vi|>": 50277,
-  "<|yi|>": 50334,
-  "<|yo|>": 50324,
-  "<|zh|>": 50259
+  "<|af|>": 50327,
+  "<|am|>": 50334,
+  "<|ar|>": 50272,
+  "<|as|>": 50350,
+  "<|az|>": 50304,
+  "<|ba|>": 50355,
+  "<|be|>": 50330,
+  "<|bg|>": 50292,
+  "<|bn|>": 50302,
+  "<|bo|>": 50347,
+  "<|br|>": 50309,
+  "<|bs|>": 50315,
+  "<|ca|>": 50270,
+  "<|cs|>": 50283,
+  "<|cy|>": 50297,
+  "<|da|>": 50285,
+  "<|de|>": 50261,
+  "<|el|>": 50281,
+  "<|endoftext|>": 50257,
+  "<|en|>": 50259,
+  "<|es|>": 50262,
+  "<|et|>": 50307,
+  "<|eu|>": 50310,
+  "<|fa|>": 50300,
+  "<|fi|>": 50277,
+  "<|fo|>": 50338,
+  "<|fr|>": 50265,
+  "<|gl|>": 50319,
+  "<|gu|>": 50333,
+  "<|haw|>": 50352,
+  "<|ha|>": 50354,
+  "<|hi|>": 50276,
+  "<|hr|>": 50291,
+  "<|ht|>": 50339,
+  "<|hu|>": 50286,
+  "<|hy|>": 50312,
+  "<|id|>": 50275,
+  "<|is|>": 50311,
+  "<|it|>": 50274,
+  "<|iw|>": 50279,
+  "<|ja|>": 50266,
+  "<|jw|>": 50356,
+  "<|ka|>": 50329,
+  "<|kk|>": 50316,
+  "<|km|>": 50323,
+  "<|kn|>": 50306,
+  "<|ko|>": 50264,
+  "<|la|>": 50294,
+  "<|lb|>": 50345,
+  "<|ln|>": 50353,
+  "<|lo|>": 50336,
+  "<|lt|>": 50293,
+  "<|lv|>": 50301,
+  "<|mg|>": 50349,
+  "<|mi|>": 50295,
+  "<|mk|>": 50308,
+  "<|ml|>": 50296,
+  "<|mn|>": 50314,
+  "<|mr|>": 50320,
+  "<|ms|>": 50282,
+  "<|mt|>": 50343,
+  "<|my|>": 50346,
+  "<|ne|>": 50313,
+  "<|nl|>": 50271,
+  "<|nn|>": 50342,
+  "<|nocaptions|>": 50362,
+  "<|notimestamps|>": 50363,
+  "<|no|>": 50288,
+  "<|oc|>": 50328,
+  "<|pa|>": 50321,
+  "<|pl|>": 50269,
+  "<|ps|>": 50340,
+  "<|pt|>": 50267,
+  "<|ro|>": 50284,
+  "<|ru|>": 50263,
+  "<|sa|>": 50344,
+  "<|sd|>": 50332,
+  "<|si|>": 50322,
+  "<|sk|>": 50298,
+  "<|sl|>": 50305,
+  "<|sn|>": 50324,
+  "<|so|>": 50326,
+  "<|sq|>": 50317,
+  "<|sr|>": 50303,
+  "<|startoflm|>": 50360,
+  "<|startofprev|>": 50361,
+  "<|startoftranscript|>": 50258,
+  "<|su|>": 50357,
+  "<|sv|>": 50273,
+  "<|sw|>": 50318,
+  "<|ta|>": 50287,
+  "<|te|>": 50299,
+  "<|tg|>": 50331,
+  "<|th|>": 50289,
+  "<|tk|>": 50341,
+  "<|tl|>": 50348,
+  "<|transcribe|>": 50359,
+  "<|translate|>": 50358,
+  "<|tr|>": 50268,
+  "<|tt|>": 50351,
+  "<|uk|>": 50280,
+  "<|ur|>": 50290,
+  "<|uz|>": 50337,
+  "<|vi|>": 50278,
+  "<|yi|>": 50335,
+  "<|yo|>": 50325,
+  "<|zh|>": 50260
 }

special_tokens_map.json

@@ -1,5 +1,6 @@
 {
   "additional_special_tokens": [
+    "<|endoftext|>",
     "<|startoftranscript|>",
     "<|en|>",
     "<|zh|>",
@@ -107,13 +108,25 @@
     "<|nocaptions|>",
     "<|notimestamps|>"
   ],
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "unk_token": {
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
+  },
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
   }
 }

tokenizer_config.json

@@ -19,14 +19,13 @@
   },
   "errors": "replace",
   "model_max_length": 1024,
-  "name_or_path": "openai/whisper-large",
+  "name_or_path": "whisper-multi/test_added_eot",
   "pad_token": null,
-  "processor_class": "WhisperProcessor",
   "special_tokens_map_file": null,
   "tokenizer_class": "WhisperTokenizer",
   "unk_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,