You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.
import torch
def get_model ( ) :
import whisper
model = whisper . load_model ( " small " , device = ' cpu ' )
return model . encoder
def get_content ( model = None , wav_16k_tensor = None ) :
from whisper import log_mel_spectrogram , pad_or_trim
dev = next ( model . parameters ( ) ) . device
mel = log_mel_spectrogram ( wav_16k_tensor ) . to ( dev ) [ : , : 3000 ]
# if torch.cuda.is_available():
# mel = mel.to(torch.float16)
feature_len = mel . shape [ - 1 ] / / 2
assert mel . shape [ - 1 ] < 3000 , " 输入音频过长， "
with torch . no_grad ( ) :
feature = model ( pad_or_trim ( mel , 3000 ) . unsqueeze ( 0 ) ) [ : 1 , : feature_len , : ] . transpose ( 1 , 2 )
return feature