feat: CCA 唱词助手子项目 v3 — 脚本版流水线完成

新增 cca/ 子项目：编导A稿+人声音频 → ASR+AI校对+AI折行 → 5段SRT字幕。 - 讯飞录音文件转写标准版（热词注入） - DeepSeek AI校对（严格纪律：只改错别字/术语/填充词，不润色） - DeepSeek AI折行（语义断句，≤14字/行） - 节目结构自动切分（导视/正片×3/预告） - 绝对时间戳SRT输出（大洋系统兼容） Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-07-04 15:25:08 +08:00
parent 1ccb37f0c7
commit ede30d3043
21 changed files with 5530 additions and 1 deletions
@@ -0,0 +1,179 @@
+# -*- coding: utf-8 -*-
+"""
+节目结构切分器 — 将 ASR 结果按节目结构拆分为 5 段
+
+结构: 导视 + 正片(3段) + 下期预告
+标志词:
+- 导视结束 / 正片开始: "各位观众你们好" 或 "我是主持人蓝皓"
+- 正片结束: "好了观众朋友们" 或 "感谢您.*关注.*军事科技"
+- 正片之后 = 下期预告
+
+正片拆3段: 按时长大致均分，优先在角色转换处（speaker_id 变化）切分
+"""
+
+import re
+from typing import List, Tuple, Optional
+
+# 标志词模式
+PATTERN_SHOW_START = re.compile(r"各位观众你们好|我是主持人蓝皓")
+PATTERN_SHOW_END = re.compile(r"好了观众朋友们|感谢您.*关注.*军事科技|感谢您持续关注")
+
+
+def find_segment_boundaries(
+    sentences: List[Tuple[int, int, str, int]],
+) -> Tuple[int, int]:
+    """
+    找到正片开始和结束的句子索引。
+    返回 (show_start_idx, show_end_idx)
+    - show_start_idx: "各位观众你们好"所在句子的索引
+    - show_end_idx: "好了观众朋友们"所在句子的索引
+    """
+    show_start_idx = 0
+    show_end_idx = len(sentences) - 1
+
+    for i, (_, _, text, _) in enumerate(sentences):
+        if PATTERN_SHOW_START.search(text):
+            show_start_idx = i
+            break
+
+    for i in range(len(sentences) - 1, -1, -1):
+        _, _, text, _ = sentences[i]
+        if PATTERN_SHOW_END.search(text):
+            show_end_idx = i
+            break
+
+    return show_start_idx, show_end_idx
+
+
+def split_show_into_three(
+    sentences: List[Tuple[int, int, str, int]],
+    start_idx: int,
+    end_idx: int,
+) -> Tuple[int, int]:
+    """
+    将正片（start_idx 到 end_idx）拆成 3 段。
+    返回两个切分点索引 (split1_idx, split2_idx)
+
+    策略: 按时长三等分，然后在附近找 speaker_id 变化的位置。
+    """
+    if end_idx - start_idx < 6:
+        # 太短了，均分
+        third = (end_idx - start_idx) // 3
+        return start_idx + third, start_idx + 2 * third
+
+    show_start_ms = sentences[start_idx][0]
+    show_end_ms = sentences[end_idx][1]
+    total_duration = show_end_ms - show_start_ms
+
+    target1_ms = show_start_ms + total_duration // 3
+    target2_ms = show_start_ms + 2 * total_duration // 3
+
+    split1 = _find_best_split(sentences, start_idx, end_idx, target1_ms)
+    split2 = _find_best_split(sentences, split1 + 1, end_idx, target2_ms)
+
+    # 确保 split2 > split1
+    if split2 <= split1:
+        split2 = split1 + (end_idx - split1) // 2
+
+    return split1, split2
+
+
+def _find_best_split(
+    sentences: List[Tuple[int, int, str, int]],
+    range_start: int,
+    range_end: int,
+    target_ms: int,
+    search_window: int = 15,
+) -> int:
+    """
+    在 target_ms 附近（±search_window 句）找最佳切分点。
+    优先找 speaker_id 变化的位置，其次找 >2秒 空白。
+    """
+    # 先找到时间上最接近 target_ms 的句子
+    closest_idx = range_start
+    min_diff = abs(sentences[range_start][0] - target_ms)
+    for i in range(range_start, min(range_end + 1, len(sentences))):
+        diff = abs(sentences[i][0] - target_ms)
+        if diff < min_diff:
+            min_diff = diff
+            closest_idx = i
+
+    # 在附近找 speaker 变化点
+    search_lo = max(range_start + 1, closest_idx - search_window)
+    search_hi = min(range_end, closest_idx + search_window)
+
+    best_idx = closest_idx
+    best_score = 0
+
+    for i in range(search_lo, search_hi):
+        score = 0
+        # speaker 变化加分
+        if sentences[i][3] != sentences[i - 1][3] and sentences[i][3] != 0:
+            score += 10
+        # 空白间隔加分
+        gap = sentences[i][0] - sentences[i - 1][1]
+        if gap > 2000:
+            score += 5
+        elif gap > 1000:
+            score += 2
+        # 离目标越近加分
+        time_diff = abs(sentences[i][0] - target_ms)
+        time_score = max(0, 5 - time_diff / 10000)
+        score += time_score
+
+        if score > best_score:
+            best_score = score
+            best_idx = i
+
+    return best_idx
+
+
+def split_into_segments(
+    sentences: List[Tuple[int, int, str, int]],
+) -> List[Tuple[str, List[Tuple[int, int, str, int]]]]:
+    """
+    将全部 ASR 句子拆分为 5 段。
+    返回: [("导视", [...]), ("正片1", [...]), ("正片2", [...]), ("正片3", [...]), ("预告", [...])]
+
+    如果找不到标志词，则只输出单段。
+    """
+    if not sentences:
+        return [("正片1", [])]
+
+    show_start_idx, show_end_idx = find_segment_boundaries(sentences)
+
+    # 导视: 0 到 show_start_idx-1
+    intro = sentences[:show_start_idx] if show_start_idx > 0 else []
+
+    # 正片: show_start_idx 到 show_end_idx
+    show_sentences = sentences[show_start_idx:show_end_idx + 1]
+
+    # 预告: show_end_idx+1 到末尾
+    trailer = sentences[show_end_idx + 1:] if show_end_idx < len(sentences) - 1 else []
+
+    # 正片拆3段
+    if len(show_sentences) > 6:
+        split1, split2 = split_show_into_three(sentences, show_start_idx, show_end_idx)
+        # 转为相对于 show_sentences 的索引
+        rel_split1 = split1 - show_start_idx
+        rel_split2 = split2 - show_start_idx
+        show_part1 = show_sentences[:rel_split1]
+        show_part2 = show_sentences[rel_split1:rel_split2]
+        show_part3 = show_sentences[rel_split2:]
+    else:
+        show_part1 = show_sentences
+        show_part2 = []
+        show_part3 = []
+
+    segments = []
+    if intro:
+        segments.append(("导视", intro))
+    segments.append(("正片1", show_part1))
+    if show_part2:
+        segments.append(("正片2", show_part2))
+    if show_part3:
+        segments.append(("正片3", show_part3))
+    if trailer:
+        segments.append(("预告", trailer))
+
+    return segments