| { |
| "add_bos_token": false, |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "50522": { |
| "content": "<|startoftranscript|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50523": { |
| "content": "<|en|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50524": { |
| "content": "<|zh|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50525": { |
| "content": "<|de|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50526": { |
| "content": "<|es|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50527": { |
| "content": "<|ru|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50528": { |
| "content": "<|ko|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50529": { |
| "content": "<|fr|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50530": { |
| "content": "<|ja|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50531": { |
| "content": "<|pt|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50532": { |
| "content": "<|tr|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50533": { |
| "content": "<|pl|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50534": { |
| "content": "<|ca|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50535": { |
| "content": "<|nl|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50536": { |
| "content": "<|ar|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50537": { |
| "content": "<|sv|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50538": { |
| "content": "<|it|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50539": { |
| "content": "<|id|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50540": { |
| "content": "<|hi|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50541": { |
| "content": "<|fi|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50542": { |
| "content": "<|vi|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50543": { |
| "content": "<|he|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50544": { |
| "content": "<|uk|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50545": { |
| "content": "<|el|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50546": { |
| "content": "<|ms|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50547": { |
| "content": "<|cs|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50548": { |
| "content": "<|ro|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50549": { |
| "content": "<|da|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50550": { |
| "content": "<|hu|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50551": { |
| "content": "<|ta|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50552": { |
| "content": "<|no|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50553": { |
| "content": "<|th|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50554": { |
| "content": "<|ur|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50555": { |
| "content": "<|hr|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50556": { |
| "content": "<|bg|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50557": { |
| "content": "<|lt|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50558": { |
| "content": "<|la|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50559": { |
| "content": "<|mi|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50560": { |
| "content": "<|ml|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50561": { |
| "content": "<|cy|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50562": { |
| "content": "<|sk|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50563": { |
| "content": "<|te|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50564": { |
| "content": "<|fa|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50565": { |
| "content": "<|lv|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50566": { |
| "content": "<|bn|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50567": { |
| "content": "<|sr|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50568": { |
| "content": "<|az|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50569": { |
| "content": "<|sl|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50570": { |
| "content": "<|kn|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50571": { |
| "content": "<|et|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50572": { |
| "content": "<|mk|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50573": { |
| "content": "<|br|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50574": { |
| "content": "<|eu|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50575": { |
| "content": "<|is|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50576": { |
| "content": "<|hy|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50577": { |
| "content": "<|ne|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50578": { |
| "content": "<|mn|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50579": { |
| "content": "<|bs|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50580": { |
| "content": "<|kk|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50581": { |
| "content": "<|sq|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50582": { |
| "content": "<|sw|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50583": { |
| "content": "<|gl|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50584": { |
| "content": "<|mr|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50585": { |
| "content": "<|pa|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50586": { |
| "content": "<|si|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50587": { |
| "content": "<|km|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50588": { |
| "content": "<|sn|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50589": { |
| "content": "<|yo|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50590": { |
| "content": "<|so|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50591": { |
| "content": "<|af|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50592": { |
| "content": "<|oc|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50593": { |
| "content": "<|ka|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50594": { |
| "content": "<|be|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50595": { |
| "content": "<|tg|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50596": { |
| "content": "<|sd|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50597": { |
| "content": "<|gu|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50598": { |
| "content": "<|am|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50599": { |
| "content": "<|yi|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50600": { |
| "content": "<|lo|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50601": { |
| "content": "<|uz|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50602": { |
| "content": "<|fo|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50603": { |
| "content": "<|ht|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50604": { |
| "content": "<|ps|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50605": { |
| "content": "<|tk|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50606": { |
| "content": "<|nn|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50607": { |
| "content": "<|mt|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50608": { |
| "content": "<|sa|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50609": { |
| "content": "<|lb|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50610": { |
| "content": "<|my|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50611": { |
| "content": "<|bo|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50612": { |
| "content": "<|tl|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50613": { |
| "content": "<|mg|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50614": { |
| "content": "<|as|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50615": { |
| "content": "<|tt|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50616": { |
| "content": "<|haw|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50617": { |
| "content": "<|ln|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50618": { |
| "content": "<|ha|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50619": { |
| "content": "<|ba|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50620": { |
| "content": "<|jw|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50621": { |
| "content": "<|su|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "50622": { |
| "content": "<|translate|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50623": { |
| "content": "<|transcribe|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50624": { |
| "content": "<|startoflm|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50625": { |
| "content": "<|startofprev|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50626": { |
| "content": "<|nocaptions|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50627": { |
| "content": "<|notimestamps|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50628": { |
| "content": "<|endoftext|>", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50629": { |
| "content": "<|¡|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50630": { |
| "content": "<|¢|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50631": { |
| "content": "<|£|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50632": { |
| "content": "<|¤|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50633": { |
| "content": "<|¥|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50634": { |
| "content": "<|¦|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50635": { |
| "content": "<|§|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50636": { |
| "content": "<|¨|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50637": { |
| "content": "<|©|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50638": { |
| "content": "<|ª|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50639": { |
| "content": "<|«|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50640": { |
| "content": "<|¬|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50641": { |
| "content": "<|®|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50642": { |
| "content": "<|¯|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50643": { |
| "content": "<|°|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50644": { |
| "content": "<|±|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50645": { |
| "content": "<|²|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50646": { |
| "content": "<|³|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50647": { |
| "content": "<|´|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50648": { |
| "content": "<|µ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50649": { |
| "content": "<|¶|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50650": { |
| "content": "<|·|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50651": { |
| "content": "<|¸|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50652": { |
| "content": "<|¹|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50653": { |
| "content": "<|º|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50654": { |
| "content": "<|»|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50655": { |
| "content": "<|¼|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50656": { |
| "content": "<|½|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50657": { |
| "content": "<|¾|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50658": { |
| "content": "<|¿|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50659": { |
| "content": "<|À|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50660": { |
| "content": "<|Á|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50661": { |
| "content": "<|Â|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50662": { |
| "content": "<|Ã|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50663": { |
| "content": "<|Ä|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50664": { |
| "content": "<|Å|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50665": { |
| "content": "<|Æ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50666": { |
| "content": "<|Ç|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50667": { |
| "content": "<|È|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50668": { |
| "content": "<|É|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50669": { |
| "content": "<|Ê|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50670": { |
| "content": "<|Ë|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50671": { |
| "content": "<|Ì|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50672": { |
| "content": "<|Í|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50673": { |
| "content": "<|Î|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50674": { |
| "content": "<|Ï|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50675": { |
| "content": "<|Ð|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50676": { |
| "content": "<|Ñ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50677": { |
| "content": "<|Ò|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50678": { |
| "content": "<|Ó|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50679": { |
| "content": "<|Ô|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50680": { |
| "content": "<|Õ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50681": { |
| "content": "<|Ö|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50682": { |
| "content": "<|×|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50683": { |
| "content": "<|Ø|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50684": { |
| "content": "<|Ù|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50685": { |
| "content": "<|Ú|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50686": { |
| "content": "<|Û|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50687": { |
| "content": "<|Ü|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50688": { |
| "content": "<|Ý|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50689": { |
| "content": "<|Þ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50690": { |
| "content": "<|ß|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50691": { |
| "content": "<|à|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50692": { |
| "content": "<|á|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50693": { |
| "content": "<|â|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50694": { |
| "content": "<|ã|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50695": { |
| "content": "<|ä|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50696": { |
| "content": "<|å|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50697": { |
| "content": "<|æ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50698": { |
| "content": "<|ç|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50699": { |
| "content": "<|è|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50700": { |
| "content": "<|é|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50701": { |
| "content": "<|ê|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50702": { |
| "content": "<|ë|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50703": { |
| "content": "<|ì|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50704": { |
| "content": "<|í|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50705": { |
| "content": "<|î|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50706": { |
| "content": "<|ï|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50707": { |
| "content": "<|ð|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50708": { |
| "content": "<|ñ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50709": { |
| "content": "<|ò|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50710": { |
| "content": "<|ó|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50711": { |
| "content": "<|ô|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50712": { |
| "content": "<|õ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50713": { |
| "content": "<|ö|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50714": { |
| "content": "<|÷|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50715": { |
| "content": "<|ø|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50716": { |
| "content": "<|ù|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50717": { |
| "content": "<|ú|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50718": { |
| "content": "<|û|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50719": { |
| "content": "<|ü|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50720": { |
| "content": "<|ý|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50721": { |
| "content": "<|þ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50722": { |
| "content": "<|ÿ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50723": { |
| "content": "<|Ā|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50724": { |
| "content": "<|ā|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50725": { |
| "content": "<|Ă|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50726": { |
| "content": "<|ă|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50727": { |
| "content": "<|Ą|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50728": { |
| "content": "<|ą|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50729": { |
| "content": "<|Ć|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50730": { |
| "content": "<|ć|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50731": { |
| "content": "<|Ĉ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50732": { |
| "content": "<|ĉ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50733": { |
| "content": "<|Ċ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50734": { |
| "content": "<|ċ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50735": { |
| "content": "<|Č|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50736": { |
| "content": "<|č|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50737": { |
| "content": "<|Ď|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50738": { |
| "content": "<|ď|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50739": { |
| "content": "<|Đ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50740": { |
| "content": "<|đ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50741": { |
| "content": "<|Ē|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50742": { |
| "content": "<|ē|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50743": { |
| "content": "<|Ĕ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50744": { |
| "content": "<|ĕ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50745": { |
| "content": "<|Ė|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50746": { |
| "content": "<|ė|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50747": { |
| "content": "<|Ę|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50748": { |
| "content": "<|ę|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50749": { |
| "content": "<|Ě|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50750": { |
| "content": "<|ě|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50751": { |
| "content": "<|Ĝ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50752": { |
| "content": "<|ĝ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50753": { |
| "content": "<|Ğ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50754": { |
| "content": "<|ğ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50755": { |
| "content": "<|Ġ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50756": { |
| "content": "<|ġ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50757": { |
| "content": "<|Ģ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50758": { |
| "content": "<|ģ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50759": { |
| "content": "<|Ĥ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50760": { |
| "content": "<|ĥ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50761": { |
| "content": "<|Ħ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50762": { |
| "content": "<|ħ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50763": { |
| "content": "<|Ĩ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50764": { |
| "content": "<|ĩ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50765": { |
| "content": "<|Ī|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50766": { |
| "content": "<|ī|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50767": { |
| "content": "<|Ĭ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50768": { |
| "content": "<|ĭ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50769": { |
| "content": "<|Į|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50770": { |
| "content": "<|į|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50771": { |
| "content": "<|İ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50772": { |
| "content": "<|ı|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50773": { |
| "content": "<|IJ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50774": { |
| "content": "<|ij|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50775": { |
| "content": "<|Ĵ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50776": { |
| "content": "<|ĵ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50777": { |
| "content": "<|Ķ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50778": { |
| "content": "<|ķ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50779": { |
| "content": "<|ĸ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50780": { |
| "content": "<|Ĺ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50781": { |
| "content": "<|ĺ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50782": { |
| "content": "<|Ļ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50783": { |
| "content": "<|ļ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50784": { |
| "content": "<|Ľ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50785": { |
| "content": "<|ľ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50786": { |
| "content": "<|Ŀ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50787": { |
| "content": "<|ŀ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50788": { |
| "content": "<|Ł|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50789": { |
| "content": "<|ł|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50790": { |
| "content": "<|Ń|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50791": { |
| "content": "<|Ûķ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50792": { |
| "content": "<|ÛĮ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50793": { |
| "content": "<|ا|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50794": { |
| "content": "<|ĠØ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50795": { |
| "content": "<|ÙĪ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50796": { |
| "content": "<|ÙĨ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50797": { |
| "content": "<|ر|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50798": { |
| "content": "<|Ú©|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50799": { |
| "content": "<|ĠÙ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50800": { |
| "content": "<|ت|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50801": { |
| "content": "<|اÙĨ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50802": { |
| "content": "<|Ûİ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50803": { |
| "content": "<|د|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50804": { |
| "content": "<|Ùħ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50805": { |
| "content": "<|Ġب|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50806": { |
| "content": "<|ÛĨ|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "50807": { |
| "content": "<|س|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "additional_special_tokens": [ |
| "<|endoftext|>", |
| "<|startoftranscript|>", |
| "<|¡|>", |
| "<|¢|>", |
| "<|£|>", |
| "<|¤|>", |
| "<|¥|>", |
| "<|¦|>", |
| "<|§|>", |
| "<|¨|>", |
| "<|©|>", |
| "<|ª|>", |
| "<|«|>", |
| "<|¬|>", |
| "<|®|>", |
| "<|¯|>", |
| "<|°|>", |
| "<|±|>", |
| "<|²|>", |
| "<|³|>", |
| "<|´|>", |
| "<|µ|>", |
| "<|¶|>", |
| "<|·|>", |
| "<|¸|>", |
| "<|¹|>", |
| "<|º|>", |
| "<|»|>", |
| "<|¼|>", |
| "<|½|>", |
| "<|¾|>", |
| "<|¿|>", |
| "<|À|>", |
| "<|Á|>", |
| "<|Â|>", |
| "<|Ã|>", |
| "<|Ä|>", |
| "<|Å|>", |
| "<|Æ|>", |
| "<|Ç|>", |
| "<|È|>", |
| "<|É|>", |
| "<|Ê|>", |
| "<|Ë|>", |
| "<|Ì|>", |
| "<|Í|>", |
| "<|Î|>", |
| "<|Ï|>", |
| "<|Ð|>", |
| "<|Ñ|>", |
| "<|Ò|>", |
| "<|Ó|>", |
| "<|Ô|>", |
| "<|Õ|>", |
| "<|Ö|>", |
| "<|×|>", |
| "<|Ø|>", |
| "<|Ù|>", |
| "<|Ú|>", |
| "<|Û|>", |
| "<|Ü|>", |
| "<|Ý|>", |
| "<|Þ|>", |
| "<|ß|>", |
| "<|à|>", |
| "<|á|>", |
| "<|â|>", |
| "<|ã|>", |
| "<|ä|>", |
| "<|å|>", |
| "<|æ|>", |
| "<|ç|>", |
| "<|è|>", |
| "<|é|>", |
| "<|ê|>", |
| "<|ë|>", |
| "<|ì|>", |
| "<|í|>", |
| "<|î|>", |
| "<|ï|>", |
| "<|ð|>", |
| "<|ñ|>", |
| "<|ò|>", |
| "<|ó|>", |
| "<|ô|>", |
| "<|õ|>", |
| "<|ö|>", |
| "<|÷|>", |
| "<|ø|>", |
| "<|ù|>", |
| "<|ú|>", |
| "<|û|>", |
| "<|ü|>", |
| "<|ý|>", |
| "<|þ|>", |
| "<|ÿ|>", |
| "<|Ā|>", |
| "<|ā|>", |
| "<|Ă|>", |
| "<|ă|>", |
| "<|Ą|>", |
| "<|ą|>", |
| "<|Ć|>", |
| "<|ć|>", |
| "<|Ĉ|>", |
| "<|ĉ|>", |
| "<|Ċ|>", |
| "<|ċ|>", |
| "<|Č|>", |
| "<|č|>", |
| "<|Ď|>", |
| "<|ď|>", |
| "<|Đ|>", |
| "<|đ|>", |
| "<|Ē|>", |
| "<|ē|>", |
| "<|Ĕ|>", |
| "<|ĕ|>", |
| "<|Ė|>", |
| "<|ė|>", |
| "<|Ę|>", |
| "<|ę|>", |
| "<|Ě|>", |
| "<|ě|>", |
| "<|Ĝ|>", |
| "<|ĝ|>", |
| "<|Ğ|>", |
| "<|ğ|>", |
| "<|Ġ|>", |
| "<|ġ|>", |
| "<|Ģ|>", |
| "<|ģ|>", |
| "<|Ĥ|>", |
| "<|ĥ|>", |
| "<|Ħ|>", |
| "<|ħ|>", |
| "<|Ĩ|>", |
| "<|ĩ|>", |
| "<|Ī|>", |
| "<|ī|>", |
| "<|Ĭ|>", |
| "<|ĭ|>", |
| "<|Į|>", |
| "<|į|>", |
| "<|İ|>", |
| "<|ı|>", |
| "<|IJ|>", |
| "<|ij|>", |
| "<|Ĵ|>", |
| "<|ĵ|>", |
| "<|Ķ|>", |
| "<|ķ|>", |
| "<|ĸ|>", |
| "<|Ĺ|>", |
| "<|ĺ|>", |
| "<|Ļ|>", |
| "<|ļ|>", |
| "<|Ľ|>", |
| "<|ľ|>", |
| "<|Ŀ|>", |
| "<|ŀ|>", |
| "<|Ł|>", |
| "<|ł|>", |
| "<|Ń|>", |
| "<|Ûķ|>", |
| "<|ÛĮ|>", |
| "<|ا|>", |
| "<|ĠØ|>", |
| "<|ÙĪ|>", |
| "<|ÙĨ|>", |
| "<|ر|>", |
| "<|Ú©|>", |
| "<|ĠÙ|>", |
| "<|ت|>", |
| "<|اÙĨ|>", |
| "<|Ûİ|>", |
| "<|د|>", |
| "<|Ùħ|>", |
| "<|Ġب|>", |
| "<|ÛĨ|>", |
| "<|س|>", |
| "<|translate|>", |
| "<|transcribe|>", |
| "<|startoflm|>", |
| "<|startofprev|>", |
| "<|nocaptions|>", |
| "<|notimestamps|>" |
| ], |
| "bos_token": "<|endoftext|>", |
| "clean_up_tokenization_spaces": true, |
| "eos_token": "<|endoftext|>", |
| "errors": "replace", |
| "model_max_length": 1024, |
| "pad_token": "<|endoftext|>", |
| "processor_class": "WhisperProcessor", |
| "return_attention_mask": false, |
| "tokenizer_class": "WhisperTokenizer", |
| "unk_token": "<|endoftext|>" |
| } |
|
|