Update vc_infer_pipeline.py

vc_infer_pipeline.py

@@ -11,7 +11,6 @@ import parselmouth
 import pyworld
 import torch
 import torch.nn.functional as F
-import torchcrepe
 from scipy import signal
 
 now_dir = os.getcwd()
@@ -22,19 +21,6 @@ bh, ah = signal.butter(N=5, Wn=48, btype="high", fs=16000)
 input_audio_path2wav = {}
 
 
-@lru_cache
-def cache_harvest_f0(input_audio_path, fs, f0max, f0min, frame_period):
-    audio = input_audio_path2wav[input_audio_path]
-    f0, t = pyworld.harvest(
-        audio,
-        fs=fs,
-        f0_ceil=f0max,
-        f0_floor=f0min,
-        frame_period=frame_period,
-    )
-    f0 = pyworld.stonemask(audio, f0, t, fs)
-    return f0
-
 
 def change_rms(data1, sr1, data2, sr2, rate):  # 1是输入音频，2是输出音频,rate是2的占比
     # print(data1.max(),data2.max())
@@ -93,49 +79,7 @@ class VC(object):
         f0_max = 1100
         f0_mel_min = 1127 * np.log(1 + f0_min / 700)
         f0_mel_max = 1127 * np.log(1 + f0_max / 700)
-        if f0_method == "pm":
-            f0 = (
-                parselmouth.Sound(x, self.sr)
-                .to_pitch_ac(
-                    time_step=time_step / 1000,
-                    voicing_threshold=0.6,
-                    pitch_floor=f0_min,
-                    pitch_ceiling=f0_max,
-                )
-                .selected_array["frequency"]
-            )
-            pad_size = (p_len - len(f0) + 1) // 2
-            if pad_size > 0 or p_len - len(f0) - pad_size > 0:
-                f0 = np.pad(
-                    f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant"
-                )
-        elif f0_method == "harvest":
-            input_audio_path2wav[input_audio_path] = x.astype(np.double)
-            f0 = cache_harvest_f0(input_audio_path, self.sr, f0_max, f0_min, 10)
-            if filter_radius > 2:
-                f0 = signal.medfilt(f0, 3)
-        elif f0_method == "crepe":
-            model = "full"
-            # Pick a batch size that doesn't cause memory errors on your gpu
-            batch_size = 512
-            # Compute pitch using first gpu
-            audio = torch.tensor(np.copy(x))[None].float()
-            f0, pd = torchcrepe.predict(
-                audio,
-                self.sr,
-                self.window,
-                f0_min,
-                f0_max,
-                model,
-                batch_size=batch_size,
-                device=self.device,
-                return_periodicity=True,
-            )
-            pd = torchcrepe.filter.median(pd, 3)
-            f0 = torchcrepe.filter.mean(f0, 3)
-            f0[pd < 0.1] = 0
-            f0 = f0[0].cpu().numpy()
-        elif f0_method == "rmvpe":
+        if f0_method == "rmvpe":
             if hasattr(self, "model_rmvpe") == False:
                 from rmvpe import RMVPE