新增 Mimi 与仅用户 VAP 对比并统一流式评测

2026-10-28 22:44:36 +08:00
parent 19d4e3c767
commit 6785e3a07b
55 changed files with 6160 additions and 31 deletions
@@ -1,7 +1,7 @@
 "use client";

 import { useEffect, useMemo, useRef, useState, useId } from "react";
-import { scoreAt, scorePath, type ModelId, type ScoreResponse, type ScoreSeries } from "@/lib/model-scores";
+import { checkpointsForDisplay, scoreAt, scorePath, type ModelId, type ScoreResponse, type ScoreSeries } from "@/lib/model-scores";
 import { createPortal } from "react-dom";
 import { SCORE_MODELS, SCORE_MODEL_IDS, readScorePreferences } from "@/lib/score-models";
 import type { TimelineAnnotation } from "./timeline";
@@ -169,7 +169,8 @@ export default function ModelScoreTrack({ series, width, durationMs, currentMs,
 }) {
  const [hoverMs, setHoverMs] = useState<number | null>(null);
  const paths = useMemo(() => series.map(row => ({ ...row,
-    path: scorePath(row.points, durationMs, width, SCORE_HEIGHT, row.sample_interval_ms) })), [series, durationMs, width]);
+    checkpoints: checkpointsForDisplay(row, annotations.map(annotation => annotation.decision_ms)),
+    path: scorePath(row.points, durationMs, width, SCORE_HEIGHT, row.sample_interval_ms) })), [series, annotations, durationMs, width]);
  const y = (p: number) => 12 + (1 - p) * (SCORE_HEIGHT - 24);
  const x = (ms: number) => ms / durationMs * width;
  const inspect = hoverMs ?? currentMs;
@@ -180,7 +181,7 @@ export default function ModelScoreTrack({ series, width, durationMs, currentMs,
  };
  return <div className={styles.scoreTrack} onPointerLeave={() => setHoverMs(null)}>
    <svg width={width} height={SCORE_HEIGHT} viewBox={`0 0 ${width} ${SCORE_HEIGHT}`}
-      role="group" aria-label="VAP、Smart Turn、Silero VAD、LiveKit v1-mini 与 TurnSense 分数对比，纵轴 0 到 1，横轴与录音时间一致"
+      role="group" aria-label="VAP CPC 双声道与仅用户版本、Mimi 标准与降噪双声道、Smart Turn、Silero VAD、LiveKit v1-mini 与 TurnSense 分数对比，纵轴 0 到 1，横轴与录音时间一致"
      onPointerMove={event => {
        const bounds = event.currentTarget.getBoundingClientRect();
        setHoverMs(Math.max(0, Math.min(durationMs, (event.clientX - bounds.left) / bounds.width * durationMs)));
@@ -194,12 +195,12 @@ export default function ModelScoreTrack({ series, width, durationMs, currentMs,
        <path d={row.path} fill="none" stroke={COLORS[row.model]} strokeWidth={focusedModel === row.model ? 2.8 : 1.6} strokeLinejoin="round" pointerEvents="none" />
        {row.checkpoints.map(([ms, score]) => <circle key={ms} cx={x(ms)} cy={y(score)} r={3.8}
          fill="#fffefb" stroke={COLORS[row.model]} strokeWidth={1.8} tabIndex={0} role="button"
-          aria-label={`${row.name} 原标注点评分 ${time(ms)}，${score.toFixed(3)}，点击定位`}
+          aria-label={`${row.name} ${row.checkpoint_mode === "streaming" ? "流式判断点" : "原标注点评分"} ${time(ms)}，${score.toFixed(3)}，点击定位`}
          onPointerDown={event => event.stopPropagation()}
          onClick={event => { event.stopPropagation(); selectPoint(ms); }}
          onKeyDown={event => {
            if (event.key === "Enter" || event.key === " ") { event.preventDefault(); event.stopPropagation(); selectPoint(ms); }
-          }}><title>{row.name} · 原标注点评分 {score.toFixed(3)} · {time(ms)}</title></circle>)}
+          }}><title>{row.name} · {row.checkpoint_mode === "streaming" ? "流式判断点" : "原标注点评分"} {score.toFixed(3)} · {time(ms)}{row.checkpoint_mode === "streaming" ? ` · 最近更新 ${time(scoreAt(row.points, ms, row.sample_interval_ms * 2)![0])}` : ""}</title></circle>)}
      </g>)}
      {hoverMs !== null && <line x1={x(hoverMs)} x2={x(hoverMs)} y1={0} y2={SCORE_HEIGHT} stroke="#77816c" opacity=".5" pointerEvents="none" />}
    </svg>
@@ -345,7 +345,7 @@ export default function Timeline({
      </div>
      {scoresOpen && <div className={styles.scoreDescription} role="status">
        {scores.status === "loading" ? "正在读取模型分数…" : scores.status === "error" ? <>{scores.messages.join(" ")} <button type="button" onClick={scores.retry}>重新读取</button></>
-          : <>实线：连续回放评分 · 空心点：原标注点评分 · 虚线：参考阈值。Smart Turn、LiveKit 表示完成倾向，TurnSense 为 P(complete)；VAP 使用 1 − 用户近期发声分数，Silero 使用 1 − 当前发声分数，仅为非发声基线，不是语义 EOT 概率。{scores.messages.join(" ")}</>}
+          : <>实线：连续回放评分 · 空心点：判断时评分（VAP 为流式取点） · 虚线：参考阈值。Smart Turn、LiveKit 表示完成倾向，TurnSense 为 P(complete)；VAP 使用 1 − 用户近期发声分数，Silero 使用 1 − 当前发声分数，仅为非发声基线，不是语义 EOT 概率。{scores.messages.join(" ")}</>}
      </div>}

      <div className={styles.trackLayout}>
@@ -474,7 +474,7 @@ export default function Timeline({
        </div>
      </div>

-      {scoresOpen && scores.series.length > 0 && <p className={styles.scoreFootnote}>点击曲线定位录音；悬停查看分数。VAP 约每 100 ms、Smart Turn 每 200 ms、Silero 每 32 ms、LiveKit、TurnSense 每 200 ms 更新。TurnSense 使用过去 8 秒用户音频；LiveKit 使用过去 1.2 秒用户音频，中文参考阈值 0.355；Silero 空心点取判断前最后完整帧；VAP 和 Smart Turn 原标注点评分使用独立历史窗口，与连续曲线可能不同；TurnSense 的 0.5 参考线不等同于原生三分类取最大值规则；编辑标注或转写不会重算已有分数。</p>}
+      {scoresOpen && scores.series.length > 0 && <p className={styles.scoreFootnote}>点击曲线定位录音；悬停查看分数。VAP CPC 约每 100 ms，Mimi 标准与降噪版约每 80 ms；Smart Turn 每 200 ms、Silero 每 32 ms、LiveKit、TurnSense 每 200 ms 更新。原 VAP 为 CPC 降噪双声道，“仅用户”版将机器人输入全程置为静音；Mimi 两版均输入用户和机器人双声道，20 秒上下文。回放仍为原录音。TurnSense 使用过去 8 秒用户音频；LiveKit 使用过去 1.2 秒用户音频，中文参考阈值 0.355；Silero 空心点取判断前最后完整帧；VAP 各版本圆点与悬停分数均取判断前最后可用的连续流评分，圆点应落在对应阶梯曲线上；Smart Turn 的原判断点仍为独立窗口结果；TurnSense 的 0.5 参考线不等同于原生三分类取最大值规则；编辑标注或转写不会重跑模型；VAP 圆点随当前判断位置从连续曲线重新取点。</p>}

      <div className={styles.bottomBar}>
        <div className={styles.timeReadout}><span className={styles.playheadDot} /> 播放 <strong>{timeLabel(current, true)}</strong></div>