Commit Graph
211 Commits
Author SHA1 Message Date
Hawk Lee aaa4ec5adf fix: improved regex for hot-patching VibeVoice model code to be more robust (v1.5.00) 2025-12-29 11:04:41 +08:00
Hawk Lee 5759fb9087 fix: use robust regex hot-patching for external VibeVoice code (v1.5.00) 2025-12-29 10:33:35 +08:00
Hawk Lee 81550c923e fix: hot-patch loaded model code to prevent crashes on None inputs (v1.5.00) 2025-12-29 10:11:57 +08:00
Hawk Lee fbeea41edd fix: enforce reference_audio requirement to prevent model inference crash (v1.5.00) 2025-12-29 10:07:20 +08:00
Hawk Lee e067dd7cf1 fix: safely handle None optional inputs in VibeVoice generation (v1.5.00) 2025-12-29 10:03:47 +08:00
Hawk Lee 799e639a55 fix: monkey-patch tokenizer with VibeVoice specific attributes (v1.5.00) 2025-12-29 10:00:26 +08:00
Hawk Lee 6f7f1dd993 fix: auto-format text input with speaker tags if missing (v1.5.00) 2025-12-29 09:57:52 +08:00
Hawk Lee 2e5ae0bf9e fix: prevent repeated module loading to avoid type mismatch in AutoConfig registry (v1.5.00) 2025-12-29 09:55:59 +08:00
Hawk Lee 5c7148b147 fix: add missing vibevoice_core files and update sys.path for relative imports (v1.5.00) 2025-12-29 09:49:32 +08:00
Hawk Lee 49337afe25 fix: remove nested try block in v1.5.00 2025-12-29 09:39:57 +08:00
Hawk Lee e0bddc23ae fix: resolve syntax error and clean up module loading in v1.5.00 2025-12-29 09:33:05 +08:00
Hawk Lee 7efe3d66fe fix: resolve code duplication and try-except syntax in v1.5.00 2025-12-29 09:29:12 +08:00
Hawk Lee 5140148dd8 chore: bump version to 1.4.99 2025-12-29 01:18:35 +08:00
Hawk Lee 6fb89b083e feat: implement VibeVoiceProcessor integration and dynamic loading (v1.4.99) 2025-12-29 01:17:43 +08:00
Hawk Lee f65cda6c2f fix: pass tokenizer to VibeVoice generate (v1.4.98) 2025-12-29 01:13:37 +08:00
Hawk Lee 89a508cec6 docs: update VibeVoice instructions with Qwen tokenizer details 2025-12-29 01:09:58 +08:00
Hawk Lee 0e50c02848 fix: implement Qwen2Tokenizer fallback for VibeVoice (v1.4.97) 2025-12-29 01:06:01 +08:00
Hawk Lee 5ad35854e6 fix: clean overwrite of aiia_vibevoice_nodes.py (v1.4.96) 2025-12-29 01:00:29 +08:00
Hawk Lee 4b0b438f9b fix: refactor load_model to correct indentation (v1.4.96) 2025-12-29 00:55:31 +08:00
Hawk Lee 3065aea44b fix: bypass AutoTokenizer with explicit class loading (v1.4.95) 2025-12-29 00:52:43 +08:00
Hawk Lee c76dcd543e fix: retry register VibeVoice tokenizer mapping (v1.4.94) 2025-12-29 00:47:56 +08:00
Hawk Lee 5068594590 fix: register VibeVoice tokenizer mapping (v1.4.94) 2025-12-29 00:47:30 +08:00
Hawk Lee ffd1786f8b fix: reconcile model_type to 'vibevoice' (v1.4.93) 2025-12-29 00:41:58 +08:00
Hawk Lee be842000e3 fix: reconcile model_type mismatch for VibeVoice 1.5B (v1.4.93) 2025-12-29 00:41:18 +08:00
Hawk Lee 87c7c4e81c fix: add missing imports re/types for VibeVoice patching (v1.4.92) 2025-12-29 00:24:29 +08:00
Hawk Lee 7f7287542a fix: dynamic source patching to resolve relative imports in VibeVoice (v1.4.91) 2025-12-29 00:19:32 +08:00
Hawk Lee d00477862a fix: alias 0.5B code to support 1.5B VibeVoice loading (v1.4.90) 2025-12-29 00:13:06 +08:00
Hawk Lee 8db4823daf fix: use importlib for robust VibeVoice loading (v1.4.89) 2025-12-28 23:56:40 +08:00
Hawk Lee 3fa162f657 fix: manual registration of VibeVoice arch to bypass missing auto_map (v1.4.88) 2025-12-28 23:55:13 +08:00
Hawk Lee ebf0c25f6f fix: add deep debugging for VibeVoice loader (v1.4.87) 2025-12-28 23:49:05 +08:00
Hawk Lee 5636b2f077 fix: resolve VibeVoice loading KeyError by pre-loading AutoConfig (v1.4.86) 2025-12-28 23:47:35 +08:00
Hawk Lee 6a35123614 docs: add manual download instructions for VibeVoice (v1.4.85) 2025-12-28 23:23:07 +08:00
Hawk Lee f564ab1b3a docs: add VibeVoice usage guide (v1.4.85) 2025-12-28 23:16:04 +08:00
Hawk Lee 1f3c9b3134 feat: add Microsoft VibeVoice 1.5B support (v1.4.85) 2025-12-28 23:15:42 +08:00
Hawk Lee ce9c5a8bf4 fix: export AIIA Audio Info node correctly (v1.4.84) 2025-12-28 23:06:58 +08:00
Hawk Lee 8a26498f67 feat: add Audio Info node for metadata inspection (v1.4.83) 2025-12-28 23:03:11 +08:00
Hawk Lee ca9353b7af docs: add high_pass_hz documentation (v1.4.82) 2025-12-28 22:58:22 +08:00
Hawk Lee 2d91854dcc fix: indentation error and variable name in high pass filter logic (v1.4.82) 2025-12-28 22:51:33 +08:00
Hawk Lee 10eeb407f5 feat: add high_pass_hz parameter to remove low-freq artifacts (v1.4.81) 2025-12-28 22:50:50 +08:00
Hawk Lee a0c8a7fa32 fix: restore missing use_cuda parameter in INPUT_TYPES (v1.4.80) 2025-12-28 22:44:09 +08:00
Hawk Lee ff1b91bfd9 docs: update README with Resemble Enhance usage guide (v1.4.79) 2025-12-28 22:42:41 +08:00
Hawk Lee 543e41fd03 feat: expose denoise_strength parameter (v1.4.79) 2025-12-28 22:31:53 +08:00
Hawk Lee 3fa7309f89 fix: lowercase solver method name for compatibility (v1.4.78) 2025-12-28 22:22:51 +08:00
Hawk Lee 1810337983 fix: use official configurate_ method for model setup (v1.4.77) 2025-12-28 22:08:05 +08:00
Hawk Lee aa73a4596b fix: remove duplicate code lines in aiia_audio_enhance.py (v1.4.76) 2025-12-28 21:52:32 +08:00
Hawk Lee 133f0d6749 fix: pad last chunk to speed up compilation (v1.4.76) 2025-12-28 21:51:47 +08:00
Hawk Lee 7544c90b41 fix: update safe_merge_chunks to support arbitrary args/kwargs (v1.4.75) 2025-12-28 21:44:44 +08:00
Hawk Lee a990e447e7 fix: re-add normalization step to define abs_max (v1.4.74) 2025-12-28 21:37:35 +08:00
Hawk Lee 0d7dc8f1c7 fix: update safe_inference_chunk signature to accept sr argument (v1.4.73) 2025-12-28 21:30:07 +08:00
Hawk Lee 20b5081774 fix: restore mangled safe_inference_chunk structure logic (v1.4.72) 2025-12-28 21:23:35 +08:00