71 lines
2.2 KiB
Python
71 lines
2.2 KiB
Python
# 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/>.
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from functools import partial
|
|
from pathlib import Path
|
|
|
|
from gi.repository import Gtk
|
|
|
|
from gajim.plugins import GajimPlugin
|
|
from gajim.plugins.plugins_i18n import _
|
|
|
|
from .gtk.config_dialog import STTVoiceMessagesConfigDialog
|
|
from .gtk.sttbox import STTBox
|
|
from .model import OnnxAsrModel
|
|
|
|
log = logging.getLogger("gajim.p.stt_voice_messages")
|
|
|
|
|
|
class STTVoiceMessagesPlugin(GajimPlugin):
|
|
def init(self) -> None:
|
|
self.description = _("Transcribes voice messages to text.")
|
|
|
|
self.config_default_values = {
|
|
"auto_transcribe": (False, ""),
|
|
"model_id": ("nemo-parakeet-tdt-0.6b-v3", ""),
|
|
"quantization": ("int8", ""),
|
|
}
|
|
|
|
self._model = OnnxAsrModel(
|
|
str(self.config["model_id"]), str(self.config["quantization"])
|
|
)
|
|
self.config_dialog = partial(STTVoiceMessagesConfigDialog, self)
|
|
|
|
self.gui_extension_points = {
|
|
"preview_audio": (self._on_preview_audio, None),
|
|
}
|
|
|
|
@property
|
|
def model(self) -> OnnxAsrModel:
|
|
return self._model
|
|
|
|
def deactivate(self) -> None:
|
|
self._model.unload_now()
|
|
|
|
def _on_preview_audio(
|
|
self, drawing_box: Gtk.Box, control_box: Gtk.Box, audio_file: Path
|
|
) -> None:
|
|
content_box = drawing_box.get_parent().get_parent()
|
|
|
|
stt_box = STTBox(self._model, audio_file)
|
|
control_box.append(stt_box.button)
|
|
content_box.append(stt_box)
|
|
|
|
if self.config["auto_transcribe"]:
|
|
stt_box.transcribe()
|