78 lines
2.9 KiB
Python
78 lines
2.9 KiB
Python
import os
|
||
import logging
|
||
from faster_whisper import WhisperModel
|
||
import sqlite3
|
||
from datetime import datetime
|
||
from pydub import AudioSegment
|
||
from pathlib import Path
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
# ЖЕСТКИЙ ФИКС ПУТЕЙ К БИНАРНИКАМ
|
||
AudioSegment.converter = "/usr/bin/ffmpeg"
|
||
AudioSegment.ffprobe = "/usr/bin/ffprobe"
|
||
|
||
class VoiceService:
|
||
def __init__(self, db_path: str, model_size: str = "small"):
|
||
self.db_path = db_path
|
||
self.model_size = model_size
|
||
logger.info(f"💾 Загрузка модели Whisper ({model_size})...")
|
||
self.model = WhisperModel(model_size, device="cpu", compute_type="int8")
|
||
self._init_db()
|
||
|
||
def _init_db(self):
|
||
conn = sqlite3.connect(self.db_path)
|
||
cursor = conn.cursor()
|
||
cursor.execute('''
|
||
CREATE TABLE IF NOT EXISTS voice_recognition_logs (
|
||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||
user_id INTEGER,
|
||
username TEXT,
|
||
message_type TEXT,
|
||
duration INTEGER,
|
||
text TEXT,
|
||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||
)
|
||
''')
|
||
conn.commit()
|
||
conn.close()
|
||
|
||
def transcribe(self, file_path: str, user_id: int, username: str, msg_type: str) -> str:
|
||
f_path = Path(file_path)
|
||
if not f_path.exists():
|
||
raise FileNotFoundError(f"Файл не найден: {file_path}")
|
||
|
||
try:
|
||
logger.info(f"🔄 Конвертация {f_path.name}...")
|
||
wav_path = str(f_path.with_suffix('.wav'))
|
||
|
||
# Конвертируем
|
||
audio = AudioSegment.from_file(str(f_path))
|
||
duration = int(len(audio) / 1000)
|
||
audio.export(wav_path, format="wav")
|
||
|
||
logger.info(f"🧠 Расшифровка ({duration}с)...")
|
||
segments, info = self.model.transcribe(wav_path, beam_size=5)
|
||
text = " ".join([segment.text for segment in segments]).strip()
|
||
|
||
# Чистим за собой
|
||
if os.path.exists(wav_path): os.remove(wav_path)
|
||
|
||
self._log_to_db(user_id, username, msg_type, duration, text)
|
||
return text
|
||
except Exception as e:
|
||
logger.error(f"❌ Ошибка транскрибации: {e}", exc_info=True)
|
||
raise e
|
||
|
||
def _log_to_db(self, user_id, username, msg_type, duration, text):
|
||
try:
|
||
conn = sqlite3.connect(self.db_path)
|
||
cursor = conn.cursor()
|
||
cursor.execute('''
|
||
INSERT INTO voice_recognition_logs (user_id, username, message_type, duration, text)
|
||
VALUES (?, ?, ?, ?, ?)
|
||
''', (user_id, username, msg_type, duration, text))
|
||
conn.commit()
|
||
conn.close()
|
||
except Exception as e:
|
||
logger.error(f"DB Log error: {e}")
|