JasonandJohn | Elite Encoder 7ed6c75652 feat: Add faster whisper node as custom node (#40) ...

* feat: add real-time audio transcription and SRT generation nodes

* feat: add RETURN_NAMES to AudioTranscriptionNode class

* feat: implement RETURN_NAMES as a class method in AudioTranscriptionNode

* refactor: add real-time audio transcription node and SRT generation capabilities

* refactor: clean up imports and update class attributes in transcription nodes

* refactor: streamline audio transcription logic and improve buffer handling

* refactor: reorganize imports and streamline node registration in audio transcription

* refactor: improve code readability and structure in audio transcription node

* refactor: update SRT generation to return subtitles in JSON format

* fix warmup sentienl in transcription node

* adjust buffer logic for comfystream load_audio_tensor_stream node

* fix return_name in srt_generator node (was breaking lightgraph)

---------

Co-authored-by: John | Elite Encoder <john@eliteencoder.net>

2025-09-04 15:30:09 -07:00

..

audio_transcription.py

feat: Add faster whisper node as custom node (#40)

2025-09-04 15:30:09 -07:00

face_mesh.py

feat: add MediaPipe FaceMesh node and utilities (#13)

2025-03-28 20:05:49 +01:00

feature_bank.py

feat: expose feature bank to comfyui (#12)

2025-03-28 18:01:53 +01:00

super_resolution.py

Super resolution (#18)

2025-04-04 17:21:47 -04:00