xiaoxia
f4b4f1fc4f
CI/CD Pipeline / Validate Code Quality And Tests (push) Has been cancelled
CI/CD Pipeline / Unit Tests (push) Has been cancelled
CI/CD Pipeline / Integration Tests (push) Has been cancelled
CI/CD Pipeline / Frontend Lint (push) Has been cancelled
CI/CD Pipeline / Build & Push Staging (Watchtower auto-deploy) (push) Has been cancelled
CI/CD Pipeline / Staging E2E Tests (push) Has been cancelled
CI/CD Pipeline / Staging API Integration Tests (push) Has been cancelled
CI/CD Pipeline / Build Production Runtime Images (push) Has been cancelled
CI/CD Pipeline / Deploy Production (push) Has been cancelled
CI/CD Pipeline / Production Browser E2E (push) Has been cancelled
feat: ASR自动字幕能力
48 lines
1.3 KiB
Python
Executable File
48 lines
1.3 KiB
Python
Executable File
"""ASR（语音识别）服务接口 — Port 层。"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from abc import ABC, abstractmethod
|
|
from pathlib import Path
|
|
from typing import Optional
|
|
|
|
from packages.domain.subtitle import SubtitleTimeline
|
|
|
|
|
|
class ASRService(ABC):
|
|
"""ASR 服务抽象接口。
|
|
|
|
不同的 ASR 后端（Whisper、阿里云、腾讯云等）实现此接口，
|
|
上层业务代码只依赖接口，不依赖具体实现。
|
|
"""
|
|
|
|
@abstractmethod
|
|
def transcribe(
|
|
self,
|
|
audio_path: Path,
|
|
language: Optional[str] = None,
|
|
with_word_timestamps: bool = True,
|
|
) -> SubtitleTimeline:
|
|
"""将音频文件转写为带时间轴的字幕。
|
|
|
|
Args:
|
|
audio_path: 音频文件路径（支持 wav/mp3/m4a 等常见格式）
|
|
language: 指定语言代码（zh/en/ja 等），None 表示自动检测
|
|
with_word_timestamps: 是否返回词级时间戳
|
|
|
|
Returns:
|
|
SubtitleTimeline 字幕时间轴对象
|
|
|
|
Raises:
|
|
ASRServiceError: 识别服务调用失败
|
|
"""
|
|
...
|
|
|
|
|
|
class ASRServiceError(Exception):
|
|
"""ASR 服务调用异常。"""
|
|
|
|
def __init__(self, message: str, provider: str = "unknown"):
|
|
self.provider = provider
|
|
super().__init__(f"[{provider}] {message}")
|