fe5cc633ff
* Add transcribe_chat_whisper_cpp.py: macOS whisper.cpp transcription whisper.cpp variant of transcribe_chat.py for Apple Silicon Macs. Advantages over transcribe_chat.py: - Uses whisper-cpp CLI with Metal/ANE GPU acceleration (3-5x faster) - No PyTorch or openai/whisper Python dependency - Same idempotent, crash-safe design as transcribe_chat.py - Auto-detects model from common macOS locations: ~/Library/Application Support/whisper-cpp/, ~/Library/Application Support/Recordly/whisper/, etc. - --model-size flag for automatic download if no model found - Configurable --language (default: zh) and --threads Usage: python3 transcribe_chat_whisper_cpp.py <input.json> [output.json] * refactor: 将 whisper.cpp 转为后端选项集成到 mcp_server.py 中 根据 PR #78 review 反馈，将独立的 transcribe_chat_whisper_cpp.py 重构为 mcp_server.py 中的 whisper_cpp 后端，与 PR #66 OpenAl 后端模式对齐。 变更: - mcp_server.py: 新增 _transcribe_whisper_cpp()、_resolve_whisper_cpp_binary()、 _resolve_whisper_cpp_model()，更新 _resolve_active_backend()/_cache_signature()/ _transcribe() 以分发至 whisper_cpp 后端 - transcribe_chat.py: 统一入口 mcp_server._transcribe 自动支持新后端， 仅补充了 backend 打印信息 - 删除 transcribe_chat_whisper_cpp.py config.json 启用方式: "transcription_backend": "whisper_cpp", "whisper_cpp_binary": "...", # 可选，默认自动检测 "whisper_cpp_model": "...", # 可选，默认自动检测 "whisper_cpp_language": "zh", # 可选 "whisper_cpp_threads": 4 # 可选，默认自动检测 * docs: 在语音转录隐私章节补充 whisper.cpp 后端说明 根据 PR #78 review 反馈，在 README.md ⚠️ 语音转录隐私章节 新增 whisper.cpp 后端（macOS Metal GPU 加速）的配置说明、隐私 属性和回退行为，与 OpenAI 后端并列。
112 lines
4.1 KiB
Python
112 lines
4.1 KiB
Python
"""
|
||
为聊天导出 JSON 中的语音消息补齐转录文本。
|
||
|
||
用法:
|
||
.venv/bin/python3 transcribe_chat.py <input.json> [output.json]
|
||
|
||
参数:
|
||
<input.json> 由 export_chat.py 产出的 JSON。
|
||
[output.json] 可选输出路径，默认 "<input>_transcribed.json"。
|
||
|
||
完整流程示例:
|
||
.venv/bin/python3 export_chat.py <chat_name> /tmp/chat.json
|
||
.venv/bin/python3 transcribe_chat.py /tmp/chat.json /tmp/chat_transcribed.json
|
||
|
||
行为说明:
|
||
- 后端由 config.json 中 transcription_backend 字段控制 (local/openai/whisper_cpp)，
|
||
与 MCP transcribe_voice 工具共享配置。详见 README "语音转录隐私" 章节。
|
||
- 默认 local: 使用本地 Whisper (CPU，单线程)，首次运行下载 ~145 MB 权重。
|
||
- 切到 openai: 语音上传至 OpenAI 服务器转录 (~$0.006/分钟)。
|
||
- 切到 whisper_cpp: 使用 whisper-cpp CLI (Metal GPU 加速，仅 macOS)。
|
||
- 幂等: 已有 "transcription" 字段的消息会被跳过，因此崩溃/中断后可安全重跑。
|
||
- 崩溃安全: 每处理完一条即整体重写输出 JSON，进程中断最多丢失当前一条。
|
||
|
||
需要 WeChat DB 仍然在线/已解密 —— 语音 blob 是从 DB 现场按 local_id 读取的，
|
||
不从 JSON 读。
|
||
"""
|
||
import json
|
||
import os
|
||
import sys
|
||
from datetime import datetime
|
||
|
||
import mcp_server
|
||
|
||
|
||
def _transcribe_local_id(username, local_id, backend):
|
||
row = mcp_server._fetch_voice_row(username, local_id)
|
||
if row is None:
|
||
return "[not found]"
|
||
|
||
voice_data, create_time = row
|
||
try:
|
||
wav_path, _ = mcp_server._silk_to_wav(voice_data, create_time, username, local_id)
|
||
except Exception as e:
|
||
return f"[decode error: {e}]"
|
||
|
||
try:
|
||
result = mcp_server._transcribe(wav_path, backend)
|
||
return result["text"]
|
||
except Exception as e:
|
||
return f"[transcribe error: {e}]"
|
||
|
||
|
||
def transcribe_export(input_path, output_path):
|
||
with open(input_path, encoding="utf-8") as f:
|
||
data = json.load(f)
|
||
|
||
# 优先使用导出 JSON 中已记录的 username，避免重新模糊匹配导致同名联系人漂移。
|
||
username = data.get("username")
|
||
chat_name = data.get("chat", "")
|
||
if not username:
|
||
username = mcp_server.resolve_username(chat_name)
|
||
if not username:
|
||
print(f"Could not resolve username for: {chat_name}")
|
||
sys.exit(1)
|
||
|
||
messages = data["messages"]
|
||
# Compact format: type is absent for text; transcription is only present when filled.
|
||
pending = [m for m in messages if m.get("type") == "voice" and not m.get("transcription")]
|
||
total = len(pending)
|
||
|
||
if total == 0:
|
||
print("No voice messages to transcribe.")
|
||
return
|
||
|
||
backend = mcp_server._resolve_active_backend()
|
||
print(f"Found {total} voice messages to transcribe.")
|
||
print(f"Backend: {backend}")
|
||
if backend == "local":
|
||
print("Loading Whisper model (first run downloads ~145MB)...")
|
||
mcp_server._get_whisper_model()
|
||
print("Model ready.\n")
|
||
elif backend == "whisper_cpp":
|
||
print("Using whisper-cpp with Metal GPU acceleration\n")
|
||
else:
|
||
print("")
|
||
|
||
for i, msg in enumerate(pending, 1):
|
||
local_id = msg["local_id"]
|
||
ts = msg["timestamp"]
|
||
ts_str = datetime.fromtimestamp(ts).strftime("%Y-%m-%d %H:%M:%S") if isinstance(ts, (int, float)) else ts
|
||
print(f"[{i}/{total}] local_id={local_id} ({ts_str}) ... ", end="", flush=True)
|
||
result = _transcribe_local_id(username, local_id, backend)
|
||
msg["transcription"] = result
|
||
print(repr(result[:60]) if result else '""')
|
||
|
||
# Save after each transcription so progress isn't lost on crash
|
||
with open(output_path, "w", encoding="utf-8") as f:
|
||
json.dump(data, f, ensure_ascii=False, indent=2)
|
||
|
||
print(f"\nDone. Written to {output_path}")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
if len(sys.argv) < 2:
|
||
print("Usage: python3 transcribe_chat.py <input.json> [output.json]")
|
||
sys.exit(1)
|
||
|
||
inp = sys.argv[1]
|
||
base, ext = os.path.splitext(inp)
|
||
out = sys.argv[2] if len(sys.argv) > 2 else f"{base}_transcribed{ext}"
|
||
transcribe_export(inp, out)
|