preprocessor/tokenizer_config.yaml

name: whisper_bpe_tokenizer
config_type: preprocessor
max_length: 448
truncation_strategy: longest_first
truncation_direction: right
stride: 0
padding_strategy: longest
padding_direction: right
pad_to_multiple_of: 0
pad_token_type_id: 0
bos_token: <|startoftranscript|>
eos_token: <|endoftext|>
unk_token: <|endoftext|>
pad_token: <|endoftext|>
additional_special_tokens:
- <|endoftext|>
- <|endoftext|>
- <|startoftranscript|>
- <|en|>
- <|zh|>
- <|de|>
- <|es|>
- <|ru|>
- <|ko|>
- <|fr|>
- <|ja|>
- <|pt|>
- <|tr|>
- <|pl|>
- <|ca|>
- <|nl|>
- <|ar|>
- <|sv|>
- <|it|>
- <|id|>
- <|hi|>
- <|fi|>
- <|vi|>
- <|he|>
- <|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|>
continuing_subword_prefix: ''
end_of_word_suffix: ''
fuse_unk: false
vocab_size: 50364
min_frequency: 2
limit_alphabet: 1000
initial_alphabet: []
show_progress: true
translate_token: <|translate|>
transcribe_token: <|transcribe|>
notimestamps_token: <|notimestamps|>
add_prefix_space: false
add_bos_token: false
model_max_length: 1024
language: persian
predict_timestamps: false