LLM/WhisperLiveKit
1
0
Fork 0
mirror of https://github.com/QuentinFuxa/WhisperLiveKit.git synced 2026-04-28 09:30:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

alignatt: enable model sharing by removing hooks and centralizing session state. Solves #282

Browse Source 
Co-authored-by: Emmanuel Schmidbauer <eschmidbauer@gmail.com>
This commit is contained in:
Quentin Fuxa
2025-11-25 23:07:42 +01:00
parent 4e9f951551
commit 7faa21f95f
9 changed files with 525 additions and 373 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
whisperlivekit/parse_args.py
View File

@@ -296,14 +296,6 @@ def parse_args():
help="Direct path to the SimulStreaming Whisper .pt model file. Overrides --model for SimulStreaming backend.",
)
simulstreaming_group.add_argument(
"--preload-model-count",
type=int,
default=1,
dest="preload_model_count",
help="Optional. Number of models to preload in memory to speed up loading (set up to the expected number of concurrent instances).",
)
simulstreaming_group.add_argument(
"--nllb-backend",
type=str,