Spaces:
Runtime error
Runtime error
File size: 2,457 Bytes
8437114 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
from collections import Counter
from typing import Dict
import torch
from fairseq.file_chunker_utils import Chunker
from fairseq.file_io import PathManager
from fairseq.tokenizer import tokenize_line
class Binarizer:
@staticmethod
def binarize(
filename,
dict,
consumer,
tokenize=tokenize_line,
append_eos=True,
reverse_order=False,
offset=0,
end=-1,
already_numberized=False,
) -> Dict[str, int]:
nseq, ntok = 0, 0
replaced = Counter()
def replaced_consumer(word, idx):
if idx == dict.unk_index and word != dict.unk_word:
replaced.update([word])
with Chunker(
PathManager.get_local_path(filename), offset, end
) as line_iterator:
for line in line_iterator:
if already_numberized:
id_strings = line.strip().split()
id_list = [int(id_string) for id_string in id_strings]
if reverse_order:
id_list.reverse()
if append_eos:
id_list.append(dict.eos())
ids = torch.IntTensor(id_list)
else:
ids = dict.encode_line(
line=line,
line_tokenizer=tokenize,
add_if_not_exist=False,
consumer=replaced_consumer,
append_eos=append_eos,
reverse_order=reverse_order,
)
nseq += 1
ntok += len(ids)
consumer(ids)
return {
"nseq": nseq,
"nunk": sum(replaced.values()),
"ntok": ntok,
"replaced": replaced,
}
@staticmethod
def binarize_alignments(
filename, alignment_parser, consumer, offset=0, end=-1
) -> Dict[str, int]:
nseq = 0
with Chunker(
PathManager.get_local_path(filename), offset, end
) as line_iterator:
for line in line_iterator:
ids = alignment_parser(line)
nseq += 1
consumer(ids)
return {"nseq": nseq}
|