104da381fb
Extract duplicated code (Whisper loading, audio recording, transcription, VAD processing) into reusable sttlib/ package. Rewrite all 3 scripts as thin wrappers. Add 24 unit tests with mocked hardware. Fix GPU fallback bug in assistant.py and args.system assignment bug.
16 lines
534 B
Python
16 lines
534 B
Python
import os
|
|
from faster_whisper import WhisperModel
|
|
|
|
os.environ["CT2_CUDA_ALLOW_FP16"] = "1"
|
|
|
|
|
|
def load_whisper_model(model_size):
|
|
"""Load Whisper with GPU (cuda/float16) -> CPU (cpu/int8) fallback."""
|
|
print(f"Loading Whisper model ({model_size})...")
|
|
try:
|
|
return WhisperModel(model_size, device="cuda", compute_type="float16")
|
|
except Exception as e:
|
|
print(f"GPU loading failed: {e}")
|
|
print("Falling back to CPU (int8)")
|
|
return WhisperModel(model_size, device="cpu", compute_type="int8")
|