openai
/
whisper-large-v2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Upload processor

This commit is contained in:
Arthur Zucker 2022-12-05 18:45:50 +00:00 committed by huggingface-web
parent 13bde75550
commit 767312cb2d
7 changed files with 118535 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

109
added_tokens.json Normal file
View File

@ -0,0 +1,109 @@
{
"<|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
}

50000
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

1742
normalizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

16256
preprocessor_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

133
special_tokens_map.json Normal file
View File

@ -0,0 +1,133 @@
{
"additional_special_tokens": [
"<|endoftext|>",
"<|startoftranscript|>",
"<|en|>",
"<|zh|>",
"<|de|>",
"<|es|>",
"<|ru|>",
"<|ko|>",
"<|fr|>",
"<|ja|>",
"<|pt|>",
"<|tr|>",
"<|pl|>",
"<|ca|>",
"<|nl|>",
"<|ar|>",
"<|sv|>",
"<|it|>",
"<|id|>",
"<|hi|>",
"<|fi|>",
"<|vi|>",
"<|iw|>",
"<|uk|>",
"<|el|>",
"<|ms|>",
"<|cs|>",
"<|ro|>",
"<|da|>",
"<|hu|>",
"<|ta|>",
"<|no|>",
"<|th|>",
"<|ur|>",
"<|hr|>",
"<|bg|>",
"<|lt|>",
"<|la|>",
"<|mi|>",
"<|ml|>",
"<|cy|>",
"<|sk|>",
"<|te|>",
"<|fa|>",
"<|lv|>",
"<|bn|>",
"<|sr|>",
"<|az|>",
"<|sl|>",
"<|kn|>",
"<|et|>",
"<|mk|>",
"<|br|>",
"<|eu|>",
"<|is|>",
"<|hy|>",
"<|ne|>",
"<|mn|>",
"<|bs|>",
"<|kk|>",
"<|sq|>",
"<|sw|>",
"<|gl|>",
"<|mr|>",
"<|pa|>",
"<|si|>",
"<|km|>",
"<|sn|>",
"<|yo|>",
"<|so|>",
"<|af|>",
"<|oc|>",
"<|ka|>",
"<|be|>",
"<|tg|>",
"<|sd|>",
"<|gu|>",
"<|am|>",
"<|yi|>",
"<|lo|>",
"<|uz|>",
"<|fo|>",
"<|ht|>",
"<|ps|>",
"<|tk|>",
"<|nn|>",
"<|mt|>",
"<|sa|>",
"<|lb|>",
"<|my|>",
"<|bo|>",
"<|tl|>",
"<|mg|>",
"<|as|>",
"<|tt|>",
"<|haw|>",
"<|ln|>",
"<|ha|>",
"<|ba|>",
"<|jw|>",
"<|su|>",
"<|translate|>",
"<|transcribe|>",
"<|startoflm|>",
"<|startofprev|>",
"<|nocaptions|>",
"<|notimestamps|>"
],
"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
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

36
tokenizer_config.json Normal file
View File

@ -0,0 +1,36 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1024,
"name_or_path": "openai/whisper-large",
"pad_token": null,
"processor_class": "WhisperProcessor",
"return_attention_mask": false,
"special_tokens_map_file": null,
"tokenizer_class": "WhisperTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

50259
vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff