doco: v2说话人分段模式 — ASR说话人分离+大block拆分+三维动画解说识别

Browse Source

- asr_adapter: 新增roleType=1说话人分离参数，新增parse_order_result_with_speaker()，write_asr_result自动输出asr_v2_timed_spk.txt

- fusion_align: 新增speaker-aware alignment v2流程（_annotate_b_lines_with_speakers区间匹配、_detect_speaker_blocks、SYSTEM_PROMPT_SPEAKER_ALIGN大block拆分prompt、_build_broadcast_segments支持block内多段拆分）

- cli: 兼容v1/v2 stats字典

- 新增convert_to_md.py（20期融合A稿docx转md+YAML frontmatter）

- backup_before_spk/: 修改前代码备份

...

This commit is contained in:

simonkoson

2026-06-24 16:26:05 +08:00

parent a87f453326

commit 1c3963d17c

14 changed files with 13069 additions and 266 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

doco/backup_before_spk/fusion_align.py

+1761

File diff suppressed because it is too large Load Diff