mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 13:20:39 -07:00
Jamie Pine
5fd95b3dcc
Route MLX load, inference, unload, reset, cache cleanup, and shutdown through a single worker. Add affinity and concurrent-unload regression coverage.\n\nVerified: 17 related backend tests; frontend CI; cargo check.
21 lines
499 B
Python
21 lines
499 B
Python
"""
|
|
STT (Speech-to-Text) module - delegates to backend abstraction layer.
|
|
"""
|
|
|
|
from ..backends import STTBackend, get_stt_backend, unload_backend
|
|
|
|
|
|
def get_whisper_model() -> STTBackend:
|
|
"""
|
|
Get STT backend instance (MLX or PyTorch based on platform).
|
|
|
|
Returns:
|
|
STT backend instance
|
|
"""
|
|
return get_stt_backend()
|
|
|
|
|
|
async def unload_whisper_model():
|
|
"""Unload Whisper model to free memory, serialized onto the MLX worker."""
|
|
await unload_backend(get_stt_backend())
|