experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Extend Python Alphabet with config file and decode method

Browse Source
This commit is contained in:
Reuben Morais 2018-11-02 13:39:27 -03:00
parent 8b0abd5364
commit bb4551caa9
2 changed files with 11 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
DeepSpeech.py
View File

@ -30,7 +30,7 @@ from util.feeding import DataSet, ModelFeeder
from util.preprocess import preprocess from util.preprocess import preprocess
from util.gpu import get_available_gpus from util.gpu import get_available_gpus
from util.shared_lib import check_cupti from util.shared_lib import check_cupti
from util.text import sparse_tensor_value_to_texts, wer, levenshtein, Alphabet, ndarray_to_text from util.text import sparse_tensor_value_to_texts, wer, levenshtein, Alphabet
from xdg import BaseDirectory as xdg from xdg import BaseDirectory as xdg
import numpy as np import numpy as np

16
util/text.py
View File

@ -10,6 +10,7 @@ from functools import reduce
class Alphabet(object): class Alphabet(object):
def __init__(self, config_file): def __init__(self, config_file):
self._config_file = config_file
self._label_to_str = [] self._label_to_str = []
self._str_to_label = {} self._str_to_label = {}
self._size = 0 self._size = 0
@ -29,9 +30,18 @@ class Alphabet(object):
def label_from_string(self, string): def label_from_string(self, string):
return self._str_to_label[string] return self._str_to_label[string]
def decode(self, labels):
res = ''
for label in labels:
res += self.string_from_label(label)
return res
def size(self): def size(self):
return self._size return self._size
def config_file(self):
return self._config_file
def text_to_char_array(original, alphabet): def text_to_char_array(original, alphabet):
r""" r"""
Given a Python string ``original``, remove unsupported characters, map characters Given a Python string ``original``, remove unsupported characters, map characters
@ -76,12 +86,6 @@ def sparse_tuple_to_texts(tuple, alphabet):
# List of strings # List of strings
return results return results
def ndarray_to_text(value, alphabet):
results = ''
for i in range(len(value)):
results += alphabet.string_from_label(value[i])
return results
def wer(original, result): def wer(original, result):
r""" r"""
The WER is defined as the editing/Levenshtein distance on word level The WER is defined as the editing/Levenshtein distance on word level