Update README.md

README.md

@@ -39,47 +39,18 @@ model = AutoModel.from_pretrained('Tabgac/SpectPrompt', trust_remote_code=True)
 device = model.device
 # sample rate: 16k
 music_path = '/path/to/music.wav'
+# 1. get logmelspectrogram
+# get the file wav_to_mel.py from https://github.com/taugastcn/SpectPrompt.git
+from wav_to_mel import wav_to_mel
+lms = wav_to_mel(music_path)
 
-# 1. extract logmel spectrogram
-# 1.1 parameters
-class FFT_parameters:
-  sample_rate = 16000
-  window_size = 400
-  n_fft = 400
-  hop_size = 160
-  n_mels = 80
-  f_min = 50
-  f_max = 8000
-prms = FFT_parameters()
-# 1.2. extract
-import nnAudio.Spectrogram
-import librosa
-to_spec = nnAudio.Spectrogram.MelSpectrogram(
-  sr=prms.sample_rate,
-  n_fft=prms.n_fft,
-  win_length=prms.window_size,
-  hop_length=prms.hop_size,
-  n_mels=prms.n_mels,
-  fmin=prms.f_min,
-  fmax=prms.f_max,
-  center=True,
-  power=2,
-  verbose=False,
-)
-wav, ori_sr = librosa.load(music_path, mono=True, sr=prms.sample_rate)
-lms = to_spec(torch.tensor(wav))
-lms = (lms + torch.finfo().eps).log().to(device)
-# 1.3. processing
 import os
 from torch.nn.utils.rnn import pad_sequence
 import random
 # get the file transforms.py from https://github.com/taugastcn/SpectPrompt.git
 from transforms import Normalize, SpecRandomCrop, SpecPadding, SpecRepeat
-
-
 transforms = [ Normalize(-4.5, 4.5), SpecRandomCrop(target_len=2992), SpecPadding(target_len=2992), SpecRepeat() ]
 lms = lms.numpy()
-
 for trans in transforms:
   lms = trans(lms)