tcsenpai/whisperapp
1
0
Fork 0
mirror of https://github.com/tcsenpai/whisperapp.git synced 2025-06-06 23:15:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

now i removed vad

Browse Source
This commit is contained in:
tcsenpai 2025-05-23 11:55:26 +02:00
parent 6dfd4eba56
commit d5a2caed7b
1 changed files with 2 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
app.py
View File

@ -65,8 +65,7 @@ config = load_config()
DEFAULT_MODEL = config["whisper"]["default_model"] DEFAULT_MODEL = config["whisper"]["default_model"]
DEVICE = "cuda" if torch.cuda.is_available() else "cpu" DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
COMPUTE_TYPE = "float32" # Always use float32 for better compatibility COMPUTE_TYPE = "float32" # Always use float32 for better compatibility
BEAM_SIZE = config["whisper"].getint("beam_size") BATCH_SIZE = config["whisper"].getint("batch_size")
VAD_FILTER = config["whisper"].getboolean("vad_filter")
# Log device and compute type # Log device and compute type
logger.info(f"PyTorch CUDA available: {torch.cuda.is_available()}") logger.info(f"PyTorch CUDA available: {torch.cuda.is_available()}")
@ -76,7 +75,7 @@ if torch.cuda.is_available():
logger.info(f"cuDNN version: {torch.backends.cudnn.version()}") logger.info(f"cuDNN version: {torch.backends.cudnn.version()}")
logger.info(f"Using device: {DEVICE}, compute type: {COMPUTE_TYPE}") 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}, batch size: {BATCH_SIZE}"
) )
# App configuration # App configuration
@ -140,9 +139,6 @@ def transcribe_audio(
audio_file, audio_file,
language=language if language != "Auto-detect" else None, language=language if language != "Auto-detect" else None,
batch_size=16, # WhisperX uses batch_size instead of beam_size batch_size=16, # WhisperX uses batch_size instead of beam_size
vad=(
True if VAD_FILTER else False
), # WhisperX uses vad instead of vad_filter
) )
# Get the full text with timestamps # Get the full text with timestamps