First steps to multi model plugin
This commit is contained in:
92
stt_voice_messages/models/openai_whisper.py
Normal file
92
stt_voice_messages/models/openai_whisper.py
Normal file
@@ -0,0 +1,92 @@
|
||||
# This file is part of Gajim.
|
||||
#
|
||||
# Gajim 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.
|
||||
#
|
||||
# Gajim 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 Gajim. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
import typing
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from gajim.gtk.const import Setting, SettingKind, SettingType
|
||||
from gajim.gtk.preferences import PreferenceBox
|
||||
from gajim.plugins.plugins_i18n import _
|
||||
|
||||
try:
|
||||
import whisper
|
||||
OPENAI_WHISPER_AVAILABLE = True
|
||||
except ModuleNotFoundError:
|
||||
if typing.TYPE_CHECKING:
|
||||
import whisper
|
||||
|
||||
|
||||
class WhisperModel:
|
||||
def __init__(self):
|
||||
self._model_sizes = ['tiny', 'small', 'base', 'medium', 'large']
|
||||
self._multilanguage = True
|
||||
|
||||
self._config = {
|
||||
'model_size': 'tiny'
|
||||
}
|
||||
|
||||
def transcribe(self, audio_file: Path) -> str:
|
||||
model = whisper.load_model(self._config['model_size'])
|
||||
result = model.transcribe(audio_file)
|
||||
return result["text"]
|
||||
|
||||
def _build_config(self) -> list[Setting]:
|
||||
whisper_model_sizes = ('tiny', 'base', 'small', 'medium', 'large')
|
||||
settings = [
|
||||
Setting(SettingKind.COMBO,
|
||||
_('Language Model'),
|
||||
SettingType.VALUE,
|
||||
callback=self._on_setting,
|
||||
props={'combo_items': whisper_model_sizes}),
|
||||
|
||||
Setting(SettingKind.SWITCH,
|
||||
_('Use Multilanguage Model'),
|
||||
SettingType.VALUE,
|
||||
self._multilanguage,
|
||||
callback=self._on_setting,
|
||||
data='use_multilanguage_model'),
|
||||
]
|
||||
|
||||
return settings
|
||||
|
||||
def _on_setting(self, setting: Setting):
|
||||
pass
|
||||
|
||||
################################################################################
|
||||
# Whisper Settings UI
|
||||
################################################################################
|
||||
|
||||
class OpenAIWhisperGeneral(PreferenceBox):
|
||||
def __init__(self, *args: Any) -> None:
|
||||
|
||||
model_sizes = {
|
||||
'tiny': _('Tiny'),
|
||||
'small': _('Small'),
|
||||
'basic': _('Basic'),
|
||||
'medium': _('Medium'),
|
||||
'large': _('Large'),
|
||||
}
|
||||
|
||||
settings = [
|
||||
Setting(SettingKind.POPOVER,
|
||||
_('Language Model'),
|
||||
SettingType.VALUE,
|
||||
callback=None,
|
||||
props={'entries': model_sizes},
|
||||
desc=_('Model Size')),
|
||||
]
|
||||
|
||||
PreferenceBox.__init__(self, settings)
|
||||
Reference in New Issue
Block a user