2024-07-12 05:08:45 +00:00
|
|
|
import os
|
|
|
|
|
2024-07-22 16:21:45 +00:00
|
|
|
class SPieceTokenizer:
|
2024-07-12 05:08:45 +00:00
|
|
|
@staticmethod
|
|
|
|
def from_pretrained(path):
|
2024-07-22 16:21:45 +00:00
|
|
|
return SPieceTokenizer(path)
|
2024-07-12 05:08:45 +00:00
|
|
|
|
|
|
|
def __init__(self, tokenizer_path):
|
|
|
|
import sentencepiece
|
|
|
|
self.tokenizer = sentencepiece.SentencePieceProcessor(model_file=tokenizer_path)
|
|
|
|
self.end = self.tokenizer.eos_id()
|
|
|
|
|
|
|
|
def get_vocab(self):
|
|
|
|
out = {}
|
|
|
|
for i in range(self.tokenizer.get_piece_size()):
|
|
|
|
out[self.tokenizer.id_to_piece(i)] = i
|
|
|
|
return out
|
|
|
|
|
|
|
|
def __call__(self, string):
|
|
|
|
out = self.tokenizer.encode(string)
|
|
|
|
out += [self.end]
|
|
|
|
return {"input_ids": out}
|