chore: bump librosa to version 0.10.2

There is a bug in librosa 0.9.1.
librosa/librosa#1594

As a result, an error occurs when executing the "Vocals/Accompaniment Separation & Reverberation Removal" function.

To address this issue, librosa has been upgraded to version 0.10.2.
Additionally, torchcrepe has been upgraded due to its dependency on librosa.

Author: tkyaji

infer/lib/uvr5_pack/lib_v5/spec_utils.py

@@ -41,8 +41,8 @@ def wave_to_spectrogram(
         wave_left = np.asfortranarray(wave[0])
         wave_right = np.asfortranarray(wave[1])
 
-    spec_left = librosa.stft(wave_left, n_fft, hop_length=hop_length)
-    spec_right = librosa.stft(wave_right, n_fft, hop_length=hop_length)
+    spec_left = librosa.stft(wave_left, n_fft=n_fft, hop_length=hop_length)
+    spec_right = librosa.stft(wave_right, n_fft=n_fft, hop_length=hop_length)
 
     spec = np.asfortranarray([spec_left, spec_right])
 
@@ -76,7 +76,7 @@ def run_thread(**kwargs):
         kwargs={"y": wave_left, "n_fft": n_fft, "hop_length": hop_length},
     )
     thread.start()
-    spec_right = librosa.stft(wave_right, n_fft, hop_length=hop_length)
+    spec_right = librosa.stft(wave_right, n_fft=n_fft, hop_length=hop_length)
     thread.join()
 
     spec = np.asfortranarray([spec_left, spec_right])
@@ -228,26 +228,30 @@ def cache_or_load(mix_path, inst_path, mp):
 
             if d == len(mp.param["band"]):  # high-end band
                 X_wave[d], _ = librosa.load(
-                    mix_path, bp["sr"], False, dtype=np.float32, res_type=bp["res_type"]
+                    mix_path,
+                    sr=bp["sr"],
+                    mono=False,
+                    dtype=np.float32,
+                    res_type=bp["res_type"]
                 )
                 y_wave[d], _ = librosa.load(
                     inst_path,
-                    bp["sr"],
-                    False,
+                    sr=bp["sr"],
+                    mono=False,
                     dtype=np.float32,
                     res_type=bp["res_type"],
                 )
             else:  # lower bands
                 X_wave[d] = librosa.resample(
                     X_wave[d + 1],
-                    mp.param["band"][d + 1]["sr"],
-                    bp["sr"],
+                    orig_sr=mp.param["band"][d + 1]["sr"],
+                    target_sr=bp["sr"],
                     res_type=bp["res_type"],
                 )
                 y_wave[d] = librosa.resample(
                     y_wave[d + 1],
-                    mp.param["band"][d + 1]["sr"],
-                    bp["sr"],
+                    orig_sr=mp.param["band"][d + 1]["sr"],
+                    target_sr=bp["sr"],
                     res_type=bp["res_type"],
                 )
 
@@ -399,8 +403,8 @@ def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
                         mp.param["mid_side_b2"],
                         mp.param["reverse"],
                     ),
-                    bp["sr"],
-                    sr,
+                    orig_sr=bp["sr"],
+                    target_sr=sr,
                     res_type="sinc_fastest",
                 )
             else:  # mid
@@ -417,7 +421,7 @@ def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
                     ),
                 )
                 # wave = librosa.core.resample(wave2, bp['sr'], sr, res_type="sinc_fastest")
-                wave = librosa.core.resample(wave2, bp["sr"], sr, res_type="scipy")
+                wave = librosa.resample(wave2, orig_sr=bp["sr"], target_sr=sr, res_type="scipy")
 
     return wave.T
 
@@ -504,8 +508,8 @@ def ensembling(a, specs):
 def stft(wave, nfft, hl):
     wave_left = np.asfortranarray(wave[0])
     wave_right = np.asfortranarray(wave[1])
-    spec_left = librosa.stft(wave_left, nfft, hop_length=hl)
-    spec_right = librosa.stft(wave_right, nfft, hop_length=hl)
+    spec_left = librosa.stft(wave_left, n_fft=nfft, hop_length=hl)
+    spec_right = librosa.stft(wave_right, n_fft=nfft, hop_length=hl)
     spec = np.asfortranarray([spec_left, spec_right])
 
     return spec

infer/modules/uvr5/vr.py

@@ -61,20 +61,20 @@ def _path_audio_(
                 (
                     X_wave[d],
                     _,
-                ) = librosa.core.load(  # 理论上librosa读取可能对某些音频有bug，应该上av读取，但是太麻烦了弃坑
+                ) = librosa.load(  # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
                     music_file,
-                    bp["sr"],
-                    False,
+                    sr=bp["sr"],
+                    mono=False,
                     dtype=np.float32,
                     res_type=bp["res_type"],
                 )
                 if X_wave[d].ndim == 1:
                     X_wave[d] = np.asfortranarray([X_wave[d], X_wave[d]])
             else:  # lower bands
-                X_wave[d] = librosa.core.resample(
+                X_wave[d] = librosa.resample(
                     X_wave[d + 1],
-                    self.mp.param["band"][d + 1]["sr"],
-                    bp["sr"],
+                    orig_sr=self.mp.param["band"][d + 1]["sr"],
+                    target_sr=bp["sr"],
                     res_type=bp["res_type"],
                 )
             # Stft of wave source
@@ -231,20 +231,20 @@ def _path_audio_(
                 (
                     X_wave[d],
                     _,
-                ) = librosa.core.load(  # 理论上librosa读取可能对某些音频有bug，应该上av读取，但是太麻烦了弃坑
+                ) = librosa.load(  # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
                     music_file,
-                    bp["sr"],
-                    False,
+                    sr=bp["sr"],
+                    mono=False,
                     dtype=np.float32,
                     res_type=bp["res_type"],
                 )
                 if X_wave[d].ndim == 1:
                     X_wave[d] = np.asfortranarray([X_wave[d], X_wave[d]])
             else:  # lower bands
-                X_wave[d] = librosa.core.resample(
+                X_wave[d] = librosa.resample(
                     X_wave[d + 1],
-                    self.mp.param["band"][d + 1]["sr"],
-                    bp["sr"],
+                    orig_sr=self.mp.param["band"][d + 1]["sr"],
+                    target_sr=bp["sr"],
                     res_type=bp["res_type"],
                 )
             # Stft of wave source

requirements/amd.txt

@@ -3,7 +3,7 @@ joblib>=1.1.0
 numba==0.56.4
 numpy==1.23.5
 scipy
-librosa==0.9.1
+librosa==0.10.2
 llvmlite==0.39.0
 fairseq==0.12.2
 faiss-cpu==1.7.3

requirements/dml.txt

@@ -2,7 +2,7 @@ joblib>=1.1.0
 numba==0.56.4
 numpy==1.23.5
 scipy
-librosa==0.9.1
+librosa==0.10.2
 llvmlite==0.39.0
 fairseq==0.12.2
 faiss-cpu==1.7.3

requirements/ipex.txt

@@ -7,7 +7,7 @@ joblib>=1.1.0
 numba==0.56.4
 numpy==1.23.5
 scipy
-librosa==0.9.1
+librosa==0.10.2
 llvmlite==0.39.0
 fairseq==0.12.2
 faiss-cpu==1.7.3

requirements/main.txt

@@ -2,7 +2,7 @@ joblib>=1.1.0
 numba
 numpy==1.23.5
 scipy
-librosa==0.9.1
+librosa==0.10.2
 llvmlite
 fairseq
 faiss-cpu

requirements/py311.txt

@@ -2,7 +2,7 @@ joblib>=1.1.0
 numba
 numpy
 scipy
-librosa==0.9.1
+librosa==0.10.2
 llvmlite
 fairseq @ git+https://github.com/One-sixth/fairseq.git
 faiss-cpu