56 lines
1.7 KiB
Python
56 lines
1.7 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 logging
|
|
import typing
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
|
|
from ..helper import Results
|
|
from .model_settings import OpenAIWhisperSettings
|
|
from .model_template import Model
|
|
|
|
log = logging.getLogger('gajim.p.sttvm_whisper')
|
|
|
|
try:
|
|
import whisper
|
|
OPENAI_WHISPER_AVAILABLE = True
|
|
except ModuleNotFoundError:
|
|
if typing.TYPE_CHECKING:
|
|
import whisper
|
|
|
|
@dataclass
|
|
class Configuration:
|
|
model_size: str
|
|
|
|
class WhisperModel(Model):
|
|
def __init__(self):
|
|
# TODO
|
|
self._result: str = ''
|
|
self._config = OpenAIWhisperSettings()
|
|
|
|
@property
|
|
def result(self) -> str:
|
|
return self._result
|
|
|
|
def transcribe(self, result: Results, audio_file: Path) -> str:
|
|
model = whisper.load_model(self._config.model_size)
|
|
log.debug('model size is used = %s', self._config.model_size)
|
|
result.text = model.transcribe(audio_file)['text'] # pyright: ignore [reportAttributeAccessIssue]
|
|
|
|
def set_config(self, config: OpenAIWhisperSettings) -> None:
|
|
self._config = config
|
|
|