tcsenpai/whisperapp
1
0
Fork 0
mirror of https://github.com/tcsenpai/whisperapp.git synced 2025-06-07 07:25:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

tried a fix for whisper

Browse Source
This commit is contained in:
tcsenpai 2025-05-23 11:36:19 +02:00
parent 3eade21b9f
commit 696cc73e23
1 changed files with 26 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
app.py
View File

@ -28,12 +28,18 @@ config = load_config()
# Whisper configuration # Whisper configuration
DEFAULT_MODEL = config["whisper"]["default_model"] DEFAULT_MODEL = config["whisper"]["default_model"]
DEVICE = config["whisper"]["device"] if torch.cuda.is_available() else "cpu" DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
COMPUTE_TYPE = config["whisper"]["compute_type"] if DEVICE == "cuda" else "float32" COMPUTE_TYPE = "float32" # Always use float32 for better compatibility
BEAM_SIZE = config["whisper"].getint("beam_size") BEAM_SIZE = config["whisper"].getint("beam_size")
VAD_FILTER = config["whisper"].getboolean("vad_filter") VAD_FILTER = config["whisper"].getboolean("vad_filter")
logger.info(f"Initialized Whisper with device: {DEVICE}, compute type: {COMPUTE_TYPE}") # Log device and compute type
logger.info(f"PyTorch CUDA available: {torch.cuda.is_available()}")
if torch.cuda.is_available():
logger.info(f"CUDA device: {torch.cuda.get_device_name(0)}")
logger.info(f"CUDA version: {torch.version.cuda}")
logger.info(f"cuDNN version: {torch.backends.cudnn.version()}")
logger.info(f"Using device: {DEVICE}, compute type: {COMPUTE_TYPE}")
logger.info( logger.info(
f"Default model: {DEFAULT_MODEL}, beam size: {BEAM_SIZE}, VAD filter: {VAD_FILTER}" f"Default model: {DEFAULT_MODEL}, beam size: {BEAM_SIZE}, VAD filter: {VAD_FILTER}"
) )
@ -57,8 +63,23 @@ DEFAULT_OLLAMA_MODEL = ollama.get_default_model() if OLLAMA_AVAILABLE else None
def load_model(model_name: str) -> WhisperModel: def load_model(model_name: str) -> WhisperModel:
"""Load the Whisper model with the specified configuration.""" """Load the Whisper model with the specified configuration."""
logger.info(f"Loading Whisper model: {model_name}") try:
return WhisperModel(model_name, device=DEVICE, compute_type=COMPUTE_TYPE) logger.info(f"Loading Whisper model: {model_name}")
return WhisperModel(
model_name,
device=DEVICE,
compute_type=COMPUTE_TYPE,
download_root=os.path.join(os.path.dirname(__file__), "models"),
)
except Exception as e:
logger.error(f"Error loading model with CUDA: {str(e)}")
logger.info("Falling back to CPU")
return WhisperModel(
model_name,
device="cpu",
compute_type="float32",
download_root=os.path.join(os.path.dirname(__file__), "models"),
)
def transcribe_audio( def transcribe_audio(