Web   ·   Wiki   ·   Activities   ·   Blog   ·   Lists   ·   Chat   ·   Meeting   ·   Bugs   ·   Git   ·   Translate   ·   Archive   ·   People   ·   Donate
summaryrefslogtreecommitdiffstats
path: root/voice.py
blob: f6316691438b2b037f7cc3fd2b124167d278df94 (plain)
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
# Speak.activity
# A simple front end to the espeak text-to-speech engine on the XO laptop
# http://wiki.laptop.org/go/Speak
#
# Copyright (C) 2008  Joshua Minor
# This file is part of Speak.activity
#
# Parts of Speak.activity are based on code from Measure.activity
# Copyright (C) 2007  Arjun Sarwal - arjun@laptop.org
#
#     Speak.activity 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 3 of the License, or
#     (at your option) any later version.
#
#     Speak.activity 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 Speak.activity.  If not, see <http://www.gnu.org/licenses/>.

import re
import os
from gettext import gettext as _

import logging
logger = logging.getLogger('speak')

import espeak

# Lets trick gettext into generating entries
# for the voice names we expect espeak to have
# If espeak actually has new or different names
# then they won't get translated, but they
# should still show up in the interface.
expectedVoiceNames = [
    _("Portuguese (Brazil)"),
    _("Swedish"),
    _("Icelandic"),
    _("Romanian"),
    _("Swahili"),
    _("Hindi"),
    _("Dutch"),
    _("Latin"),
    _("Hungarian"),
    _("Macedonian"),
    _("Welsh"),
    _("French"),
    _("Norwegian"),
    _("Russian"),
    _("Afrikaans"),
    _("Finnish"),
    _("Default"),
    _("Cantonese"),
    _("Scottish"),
    _("Greek"),
    _("Vietnamese"),
    _("English"),
    _("Lancashire"),
    _("Italian"),
    _("Portuguese"),
    _("German"),
    _("Whisper"),
    _("Croatian"),
    _("Czech"),
    _("Slovak"),
    _("Spanish"),
    _("Polish"),
    _("Esperanto")
]

_allVoices = {}
_defaultVoice = None


class Voice:
    def __init__(self, language, name):
        self.language = language
        self.name = name
        friendlyname = name
        friendlyname = friendlyname.replace('-test', '')
        friendlyname = friendlyname.replace('_test', '')
        friendlyname = friendlyname.replace('en-', '')
        friendlyname = friendlyname.replace('english-wisper', 'whisper')
        friendlyname = friendlyname.replace('english-us', 'us')

        friendlynameRP = name  # friendlyname for RP
        friendlynameRP = friendlynameRP.replace('english_rp', 'rp')
        friendlynameRP = friendlynameRP.replace('english_wmids', 'wmids')

        parts = re.split('[ _-]', friendlyname)
        partsRP = re.split('[ _]', friendlynameRP)  # RE for english_RP
        self.short_name = _(parts[0].capitalize())
        self.friendlyname = ' '.join([self.short_name] + parts[1:])

        friendlynameRP1 = None
        if friendlynameRP == 'rp':

                friendlynameRP1 = 'English (Received Pronunciation)'
                self.friendlyname = 'English (Received Pronunciation)'

        friendlynameUS = None
        if friendlyname == 'us':
                friendlynameUS = 'English (USA)'
                self.friendlyname = 'English (USA)'

        friendlynameWMIDS = None
        if friendlynameRP == 'wmids':
                friendlynameWMIDS = 'English (West Midlands)'
                self.friendlyname = 'English (West Midlands)'

    def __cmp__(self, other):
        return cmp(self.friendlyname, other.friendlyname if other else '')


def allVoices():
    if _allVoices:
        return _allVoices

    for language, name in espeak.voices():
        voice = Voice(language, name)
        _allVoices[voice.friendlyname] = voice

    return _allVoices


def by_name(name):
    return allVoices().get(name, defaultVoice())


def defaultVoice():
    """Try to figure out the default voice, from the current locale ($LANG).
       Fall back to espeak's voice called Default."""

    global _defaultVoice

    if _defaultVoice:
        return _defaultVoice

    voices = allVoices()

    def fit(a, b):
        "Compare two language ids to see if they are similar."
        as_ = re.split(r'[^a-z]+', a.lower())
        bs = re.split(r'[^a-z]+', b.lower())
        for count in range(0, min(len(as_), len(bs))):
            if as_[count] != bs[count]:
                count -= 1
                break
        return count
    try:
        lang = os.environ["LANG"]
    except:
        lang = ""

    best = voices[_("Default")]
    for voice in voices.values():
        voiceMetric = fit(voice.language, lang)
        bestMetric = fit(best.language, lang)
        if lang == 'en_AU.UTF-8':
            if voice.friendlyname == 'English (Received Pronunciation)':
                best = voice
                break
        if voiceMetric > bestMetric:
            best = voice

    print "Best voice for LANG %s seems to be %s %s" % (lang,
                                                        best.language,
                                                        best.friendlyname)
    _defaultVoice = best
    return best