Files
gajim-plugins/stt_voice_messages/models/faster_whisper.py
2026-05-05 05:23:23 -03:00

61 lines
1.9 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 FasterWhisperSettings
from .model_template import Model
log = logging.getLogger('gajim.p.sttvm_faster_whisper')
try:
import faster_whisper
except ModuleNotFoundError:
if typing.TYPE_CHECKING:
import faster_whisper
@dataclass
class Configuration:
model_size: str
class FasterWhisperModel(Model):
def __init__(self):
self._result: str = ''
self._config = FasterWhisperSettings()
@property
def result(self) -> str:
return self._result
def transcribe(self, result: Results, audio_file: Path) -> None:
model = faster_whisper.WhisperModel(self._config.model_size, compute_type="float32")
log.debug('model size is used = %s', self._config.model_size)
segments, _ = model.transcribe(audio_file)
segments = list(segments)
result.text = ''
log.debug('segments = %s', segments)
for segment in segments:
result.text += segment.text
print("[%.2fs -> %.2fs] %s" % (
segment.start, segment.end, segment.text))
def set_config(self, config: FasterWhisperSettings) -> None:
self._config = config