FunASR/fun_text_processing/text_normalization/en/utils.py
zhifu gao 861147c730
Dev gzf exp (#1654)
* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* sensevoice finetune

* bugfix

* update with main (#1631)

* update seaco finetune

* v1.0.24

---------

Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>

* sensevoice

* sensevoice

* sensevoice

* update with main (#1638)

* update seaco finetune

* v1.0.24

* update rwkv template

---------

Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sensevoice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* sense voice

* whisper

* whisper

* update style

* update style

---------

Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
2024-04-24 16:03:38 +08:00

47 lines
1023 B
Python

import csv
import os
def get_abs_path(rel_path):
"""
Get absolute path
Args:
rel_path: relative path to this file
Returns absolute path
"""
return os.path.dirname(os.path.abspath(__file__)) + "/" + rel_path
def load_labels(abs_path):
"""
loads relative path file as dictionary
Args:
abs_path: absolute path
Returns dictionary of mappings
"""
label_tsv = open(abs_path, encoding="utf-8")
labels = list(csv.reader(label_tsv, delimiter="\t"))
return labels
def augment_labels_with_punct_at_end(labels):
"""
augments labels: if key ends on a punctuation that value does not have, add a new label
where the value maintains the punctuation
Args:
labels : input labels
Returns:
additional labels
"""
res = []
for label in labels:
if len(label) > 1:
if label[0][-1] == "." and label[1][-1] != ".":
res.append([label[0], label[1] + "."] + label[2:])
return res