Aaron Boxer 445bf26e85 Extract hardcoded buffer constants into class attributes ...

- MAX_BUFFER_DURATION_S (45): max audio buffer before trimming
- BUFFER_TRIM_DURATION_S (30): duration to discard on trim
- CLIP_THRESHOLD_DURATION_S (25): stale audio clip threshold
- CLIP_TAIL_DURATION_S (5): audio tail to keep after clipping
- All values can now be overridden by subclasses

2026-05-11 20:05:38 -04:00

..

__init__.py

Refactor 🔨

2025-03-24 16:48:33 +05:30

base.py

Extract hardcoded buffer constants into class attributes

2026-05-11 20:05:38 -04:00

faster_whisper_backend.py

Add cross-client GPU batch inference for faster_whisper backend

2026-02-26 00:00:51 +00:00

openvino_backend.py

refactor: include additional parameters

2025-04-25 13:09:44 +02:00

tokenization_small100.py

Add translation backend

2025-07-22 08:54:10 +00:00

translation_backend.py

Add translation backend

2025-07-22 08:54:10 +00:00

trt_backend.py

Merge branch 'main' into configure-more-params

2025-05-02 12:23:45 +02:00