48 lines
1.3 KiB
Python
48 lines
1.3 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/>.
|
|
|
|
import typing
|
|
from pathlib import Path
|
|
|
|
from .model import Model
|
|
|
|
from gajim.gtk.const import Setting
|
|
|
|
try:
|
|
import whisper
|
|
OPENAI_WHISPER_AVAILABLE = True
|
|
except ModuleNotFoundError:
|
|
if typing.TYPE_CHECKING:
|
|
import whisper
|
|
|
|
|
|
class WhisperModel(Model):
|
|
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 on_setting(self, setting: Setting):
|
|
pass
|
|
|