助手本体：会话引擎、LLM 路由、记忆、身份、语音适配
从 Obsidian 笔记库剥离为独立仓库。规划文档与 P0 报告留在笔记库， 代码（助手本体、TTS 服务、P0 基准脚本、ESP32 固件）在此。 架构：服务器是助手，本地是客户端 - 助手本体跑在 cadadmin-server，N5095 只做 USB 外设桥与网络桥接 - 起因：实测 N5095 无 AVX2，跑不动可用的语音模型 当前技术栈 - LLM：DeepSeek deepseek-flash（云端，必须关思考） - TTS：Qwen3-TTS 1.7B（服务器 3090，独立 HTTP 服务） - STT：Zipformer 中英双语 int8（CPU，中文识别率未测） 实测：端到端 16/16 通过，首音延迟 1545ms （对比：本地 LLM + vits-zh-ll 是 179ms，但音色不满意——音质与延迟 在此硬件上此消彼长） 设计要点 - MemoryStore 接口按"可能远程"设计（全 async、可超时、可失败） - user_id / session_id / track_id 三者分开，人脸只作候选不自动切身份 - 记忆查询强制带 owner_user_id，无按 id 单独取的口子 - 自动抽取的记忆是"候选"，默认不参与检索 - 异步写记忆绑定创建时的身份，不读"当前用户" - 引擎与传输解耦，只用文件音频即可端到端测试 模型与音频产物不进版本管理（1.1GB），由 download_models.sh 恢复
This commit is contained in:
ylhan
@@ -0,0 +1,187 @@
|
||||
#!/usr/bin/env python3
|
||||
"""P0 基准 · 本地流式 STT（sherpa-onnx 中英双语 Zipformer）。
|
||||
|
||||
测什么、为什么：
|
||||
|
||||
流式识别有两种"慢"，必须分开测，混在一起会得出错误结论。
|
||||
|
||||
1. 算法延迟（first_partial_audio_s）：要喂进多少秒音频，才吐出第一个字。
|
||||
这是模型属性（chunk 大小 + lookahead），换机器不变。它决定了"用户说完一个字到屏幕上出现字"的下限。
|
||||
|
||||
2. 算力延迟（rtf / chunk_ratio）：解码耗时与音频时长的比。
|
||||
RTF<1 表示平均能跟上实时；但平均值会骗人——只要 p95 的单块解码时间超过块的时长，
|
||||
实时场景下就会累积积压，越说越滞后。所以必须同时看 chunk_ratio 的分位数。
|
||||
|
||||
3. 收尾延迟（finalize_ms）：音频喂完后多久能拿到最终结果。
|
||||
这一段直接计入方案 P1"结束到首段有声回复"的 2 秒预算。
|
||||
|
||||
用法：
|
||||
python3 bench_stt.py # 默认线程 1,2,4
|
||||
THREADS=2 python3 bench_stt.py
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import statistics
|
||||
import sys
|
||||
import time
|
||||
import wave
|
||||
|
||||
import numpy as np
|
||||
import sherpa_onnx
|
||||
|
||||
HERE = os.path.dirname(os.path.abspath(__file__))
|
||||
STT = os.path.join(HERE, "models", "stt")
|
||||
WAVS = os.path.join(HERE, "wavs")
|
||||
SAMPLE_RATE = 16000
|
||||
CHUNK_MS = int(os.environ.get("CHUNK_MS", "100"))
|
||||
TAIL_SILENCE_S = 1.0 # 喂一段静音，让模型吐出最后一个字（真实系统里靠 VAD 判定说完）
|
||||
|
||||
|
||||
def read_wav(path):
|
||||
with wave.open(path, "rb") as w:
|
||||
assert w.getnchannels() == 1, f"{path} 不是单声道"
|
||||
assert w.getframerate() == SAMPLE_RATE, f"{path} 采样率 {w.getframerate()} != {SAMPLE_RATE}"
|
||||
pcm = w.readframes(w.getnframes())
|
||||
return np.frombuffer(pcm, dtype=np.int16).astype(np.float32) / 32768.0
|
||||
|
||||
|
||||
def build_recognizer(num_threads):
|
||||
return sherpa_onnx.OnlineRecognizer.from_transducer(
|
||||
tokens=os.path.join(STT, "tokens.txt"),
|
||||
encoder=os.path.join(STT, "encoder-epoch-99-avg-1.int8.onnx"),
|
||||
decoder=os.path.join(STT, "decoder-epoch-99-avg-1.int8.onnx"),
|
||||
joiner=os.path.join(STT, "joiner-epoch-99-avg-1.int8.onnx"),
|
||||
num_threads=num_threads,
|
||||
sample_rate=SAMPLE_RATE,
|
||||
feature_dim=80,
|
||||
decoding_method="greedy_search",
|
||||
enable_endpoint_detection=False,
|
||||
)
|
||||
|
||||
|
||||
def run_one(rec, samples):
|
||||
"""喂一遍音频，返回各项指标。"""
|
||||
chunk = int(SAMPLE_RATE * CHUNK_MS / 1000)
|
||||
stream = rec.create_stream()
|
||||
decode_times = []
|
||||
first_partial_audio_s = None
|
||||
partials = []
|
||||
|
||||
t_all = time.perf_counter()
|
||||
pos = 0
|
||||
while pos < len(samples):
|
||||
block = samples[pos:pos + chunk]
|
||||
pos += len(block)
|
||||
t0 = time.perf_counter()
|
||||
stream.accept_waveform(SAMPLE_RATE, block)
|
||||
while rec.is_ready(stream):
|
||||
rec.decode_stream(stream)
|
||||
decode_times.append(time.perf_counter() - t0)
|
||||
txt = rec.get_result(stream)
|
||||
if txt:
|
||||
partials.append((pos / SAMPLE_RATE, txt))
|
||||
if first_partial_audio_s is None:
|
||||
first_partial_audio_s = pos / SAMPLE_RATE
|
||||
|
||||
audio_s = len(samples) / SAMPLE_RATE
|
||||
|
||||
# 收尾拆成两段测，混在一起会高估"说完到出结果"的开销：
|
||||
# tail_decode_ms —— 解码尾静音的耗时。真实系统里这段对应 VAD 判定说完的等待，
|
||||
# 是"必有开销"，但与识别器算力无关，不能算进识别延迟。
|
||||
# flush_ms —— input_finished() 之后冲刷出最终结果的耗时。这才是纯识别器开销。
|
||||
t0 = time.perf_counter()
|
||||
tail = np.zeros(int(SAMPLE_RATE * TAIL_SILENCE_S), dtype=np.float32)
|
||||
pos = 0
|
||||
while pos < len(tail):
|
||||
block = tail[pos:pos + chunk]
|
||||
pos += len(block)
|
||||
stream.accept_waveform(SAMPLE_RATE, block)
|
||||
while rec.is_ready(stream):
|
||||
rec.decode_stream(stream)
|
||||
tail_decode_ms = (time.perf_counter() - t0) * 1000
|
||||
|
||||
t1 = time.perf_counter()
|
||||
stream.input_finished()
|
||||
while rec.is_ready(stream):
|
||||
rec.decode_stream(stream)
|
||||
flush_ms = (time.perf_counter() - t1) * 1000
|
||||
final_text = rec.get_result(stream)
|
||||
total_s = time.perf_counter() - t_all
|
||||
|
||||
ratios = [d / (CHUNK_MS / 1000) for d in decode_times]
|
||||
ratios_sorted = sorted(ratios)
|
||||
|
||||
def pct(xs, p):
|
||||
if not xs:
|
||||
return float("nan")
|
||||
return xs[min(len(xs) - 1, int(len(xs) * p))]
|
||||
|
||||
return {
|
||||
"audio_s": audio_s,
|
||||
"total_s": total_s,
|
||||
"rtf": total_s / (audio_s + TAIL_SILENCE_S),
|
||||
"rtf_speech_only": total_s / audio_s,
|
||||
"chunk_ratio_p50": statistics.median(ratios) if ratios else float("nan"),
|
||||
"chunk_ratio_p95": pct(ratios_sorted, 0.95),
|
||||
"chunk_ratio_max": max(ratios) if ratios else float("nan"),
|
||||
"first_partial_audio_s": first_partial_audio_s,
|
||||
"tail_decode_ms": tail_decode_ms,
|
||||
"flush_ms": flush_ms,
|
||||
"final_text": final_text,
|
||||
"n_partials": len(partials),
|
||||
}
|
||||
|
||||
|
||||
def main():
|
||||
threads_list = [int(x) for x in os.environ.get("THREADS", "1,2,4").split(",")]
|
||||
wav_files = sorted(f for f in os.listdir(WAVS) if f.endswith(".wav"))
|
||||
if not wav_files:
|
||||
sys.exit(f"没有测试音频：{WAVS}")
|
||||
|
||||
print(f"chunk={CHUNK_MS}ms 尾静音={TAIL_SILENCE_S}s 音频={wav_files}")
|
||||
print(f"CPU: 4 核 N5095（无 AVX2）\n")
|
||||
|
||||
all_results = {}
|
||||
for nt in threads_list:
|
||||
print(f"=== num_threads={nt} ===")
|
||||
rec = build_recognizer(nt)
|
||||
# 预热：首次解码包含图优化/内存分配，不计入
|
||||
warm = np.zeros(SAMPLE_RATE, dtype=np.float32)
|
||||
s = rec.create_stream()
|
||||
s.accept_waveform(SAMPLE_RATE, warm)
|
||||
while rec.is_ready(s):
|
||||
rec.decode_stream(s)
|
||||
|
||||
rows = []
|
||||
for wf in wav_files:
|
||||
samples = read_wav(os.path.join(WAVS, wf))
|
||||
r = run_one(rec, samples)
|
||||
rows.append((wf, r))
|
||||
print(f" {wf:<9} 音频{r['audio_s']:5.2f}s RTF={r['rtf']:5.2f} "
|
||||
f"块比 p50={r['chunk_ratio_p50']:.2f} p95={r['chunk_ratio_p95']:.2f} "
|
||||
f"max={r['chunk_ratio_max']:.2f} 首字@{r['first_partial_audio_s'] or float('nan'):.2f}s "
|
||||
f"冲刷={r['flush_ms']:.0f}ms")
|
||||
print(f" 识别: {r['final_text']}")
|
||||
|
||||
rtfs = [r["rtf"] for _, r in rows]
|
||||
p95s = [r["chunk_ratio_p95"] for _, r in rows]
|
||||
fin = [r["flush_ms"] for _, r in rows]
|
||||
print(f" → RTF 均值={statistics.mean(rtfs):.2f} 最差={max(rtfs):.2f} | "
|
||||
f"块比p95 最差={max(p95s):.2f} | 纯冲刷 P50={statistics.median(fin):.0f}ms "
|
||||
f"最差={max(fin):.0f}ms")
|
||||
verdict = ("可实时" if max(rtfs) < 1 and max(p95s) < 1
|
||||
else "⚠ 跟不上实时" if max(rtfs) >= 1
|
||||
else "⚠ 平均够但存在突发积压风险")
|
||||
print(f" → 判定: {verdict}\n")
|
||||
all_results[nt] = {"rows": {w: r for w, r in rows}, "verdict": verdict}
|
||||
|
||||
out = os.path.join(HERE, "results_stt.json")
|
||||
with open(out, "w") as f:
|
||||
json.dump({"chunk_ms": CHUNK_MS, "results": all_results}, f,
|
||||
ensure_ascii=False, indent=2)
|
||||
print(f"结果已写入 {out}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user