diodiogod bab68fd256 Add unified ASR node with Qwen3-ASR support

2026-01-31 11:31:09 -03:00

..

asr

Add unified ASR node with Qwen3-ASR support

2026-01-31 11:31:09 -03:00

audio

Version 4.19.5

2026-01-28 13:22:29 -03:00

compatibility

Fix Qwen3-TTS audio hash error with nested dict structure

2026-01-28 00:15:21 -03:00

device

refactor: Implement Tier 1 model loading improvements

2025-11-13 22:06:41 -03:00

downloads

Version 4.18.0

2026-01-26 23:41:36 -03:00

models

Add unified ASR node with Qwen3-ASR support

2026-01-31 11:31:09 -03:00

streaming

Add per-segment parameter switching to regular ChatterBox node (text and SRT)

2025-10-29 08:31:40 -03:00

system

Fix: Remove torchcodec dependency to eliminate FFmpeg system requirement

2025-11-05 22:26:10 -03:00

text

Version 4.19.1

2026-01-28 11:43:23 -03:00

timing

Fix Step Audio EditX local model path resolution

2025-12-08 22:08:20 -03:00

voice

Add Qwen3-TTS engine with Phase 1 implementation

2026-01-28 00:02:02 -03:00

voicefixer_bundled

Version 4.14.30

2025-11-20 00:20:37 -03:00

__init__.py

Major refactoring: Reorganize project structure for better maintainability

2025-08-02 18:50:26 -03:00

comfyui_compatibility.py

Update comments to explain PyTorch 2.9 bug fixes comprehensively

2025-11-07 03:30:36 -03:00

config_sanitizer.py

Add modular ConfigSanitizer for ComfyUI JSON serialization fix

2025-10-23 13:45:27 -03:00

ffmpeg_utils.py

Version 4.10.5

2025-09-23 21:08:05 -03:00

phoneme_matcher.py

Fix word prediction blank elimination and improve repetitive pattern variety

2025-08-15 12:12:42 -03:00

robust_import.py

Version 4.6.8

2025-08-30 00:28:43 -03:00