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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
|
# speech.py
# Copyright (C) 2010 Aleksey Lim and James D. Simmons
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
import gst
voice = 'default'
pitch = 0
rate = -20
highlight_cb = None
def _create_pipe():
pipeline = 'espeak name=source ! autoaudiosink'
pipe = gst.parse_launch(pipeline)
def stop_cb(bus, message):
pipe.set_state(gst.STATE_NULL)
def mark_cb(bus, message):
if message.structure.get_name() == 'espeak-mark':
mark = message.structure['mark']
highlight_cb(int(mark))
bus = pipe.get_bus()
bus.add_signal_watch()
bus.connect('message::eos', stop_cb)
bus.connect('message::error', stop_cb)
bus.connect('message::element', mark_cb)
return (pipe.get_by_name('source'), pipe)
def _speech(source, pipe, words):
source.props.pitch = pitch
source.props.rate = rate
source.props.voice = voice
source.props.text = words;
pipe.set_state(gst.STATE_PLAYING)
info_source, info_pipe = _create_pipe()
play_source, play_pipe = _create_pipe()
# track for marks
play_source.props.track = 2
def voices():
return info_source.props.voices
def say(words):
_speech(info_source, info_pipe, words)
print words
def play(words):
_speech(play_source, play_pipe, words)
def is_stopped():
for i in play_pipe.get_state():
if isinstance(i, gst.State) and i == gst.STATE_NULL:
return True
return False
def stop():
play_pipe.set_state(gst.STATE_NULL)
def is_paused():
for i in play_pipe.get_state():
if isinstance(i, gst.State) and i == gst.STATE_PAUSED:
return True
return False
def pause():
play_pipe.set_state(gst.STATE_PAUSED)
def rate_up():
global rate
rate = min(99, rate + 10)
def rate_down():
global rate
rate = max(-99, rate - 10)
def pitch_up():
global pitch
pitch = min(99, pitch + 10)
def pitch_down():
global pitch
pitch = max(-99, pitch - 10)
def prepare_highlighting(label_text):
i = 0
j = 0
word_begin = 0
word_end = 0
current_word = 0
word_tuples = []
omitted = [' ', '\n', u'\r', '_', '[', '{', ']', '}', '|', '<',\
'>', '*', '+', '/', '\\' ]
omitted_chars = set(omitted)
while i < len(label_text):
if label_text[i] not in omitted_chars:
word_begin = i
j = i
while j < len(label_text) and label_text[j] not in omitted_chars:
j = j + 1
word_end = j
i = j
word_t = (word_begin, word_end, label_text[word_begin: word_end].strip())
if word_t[2] != u'\r':
word_tuples.append(word_t)
i = i + 1
return word_tuples
def add_word_marks(word_tuples):
"Adds a mark between each word of text."
i = 0
marked_up_text = '<speak> '
while i < len(word_tuples):
word_t = word_tuples[i]
marked_up_text = marked_up_text + '<mark name="' + str(i) + '"/>' + word_t[2]
i = i + 1
return marked_up_text + '</speak>'
|
