Commit Graph
14 Commits
Author SHA1 Message Date
Hawk Lee eff537d9dd feat: add ASR, Podcast Splitter, and Podcast Stitcher nodes for anti-leakage pipeline
- Add AIIA_ASR node with FunASR (paraformer-zh + SenseVoiceSmall)
- Add AIIA_Podcast_Splitter for per-speaker text splitting
- Add AIIA_Podcast_Stitcher with 3-tier fuzzy alignment (exact, Levenshtein, fallback)
- Register 5 previously missing modules in __init__.py
- Update README with installation guide and node documentation
2026-02-15 12:14:45 +08:00
Hawk Lee dc1acb8c0e refactor(echomimic): rename src to echomimic_v3_src to avoid namespace collisions 2026-01-19 17:40:27 +08:00
Hawk Lee af49034a52 fix: revert highpass to single-pass to preserve bass (v1.3.12) 2025-12-28 00:55:50 +08:00
Hawk Lee 9e71159b69 feat: update default filter values to optimal (v1.3.11) 2025-12-28 00:49:08 +08:00
Hawk Lee 51381f2606 feat: add highpass filter to remove rumble (v1.3.10) 2025-12-28 00:45:21 +08:00
Hawk Lee fabf1c57c0 fix: cascade lowpass filter for steeper cutoff (v1.3.9) 2025-12-28 00:23:07 +08:00
Hawk Lee 3a317a60e9 fix: safe normalize threshold to prevent noise boosting (v1.3.8) 2025-12-28 00:13:23 +08:00
Hawk Lee 76328469b2 feat: add lowpass filter to post-process node (v1.3.7) 2025-12-27 23:53:08 +08:00
Hawk Lee 9ad8118ed9 fix: scale splice_info in post-process and bump version to 1.3.6 2025-12-27 23:44:02 +08:00
Hawk Lee 0f4dedea57 fix: use valid torchaudio resampling methods (v1.3.5) 2025-12-27 23:19:47 +08:00
Hawk Lee f9d5984603 feat: add Audio Post-Process node and bump version to 1.3.4 2025-12-27 23:01:11 +08:00
Hawk Lee 7d87825ae0 fix: Correct variable name mismatch in split_audio 2025-12-26 23:07:22 +08:00
Hawk Lee 4971419ec8 fix: Resolve NameError in split_audio and enhance robustness 2025-12-26 23:05:32 +08:00
Hawk Lee 633aaf44db feat: Introduce Audio Smart Chunker for optimized long audio splitting and CosyVoice integration 2025-12-26 22:59:05 +08:00