fix license issue

ddPn08 · ddPn08 · commit 461e8fa98d2f · 2023-05-23T10:16:31.000+09:00
diff --git a/lib/rvc/pipeline.py b/lib/rvc/pipeline.py
@@ -4,7 +4,6 @@
 
 import faiss
 import numpy as np
-import parselmouth
 import pyworld
 import scipy.signal as signal
 import torch
@@ -67,23 +66,8 @@ def get_f0(
         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":
+
+        if f0_method == "harvest":
             f0, t = pyworld.harvest(
                 x.astype(np.double),
                 fs=self.sr,
@@ -93,6 +77,17 @@ def get_f0(
             )
             f0 = pyworld.stonemask(x.astype(np.double), f0, t, self.sr)
             f0 = signal.medfilt(f0, 3)
+        elif f0_method == "dio":
+            f0, t = pyworld.dio(
+                x.astype(np.double),
+                fs=self.sr,
+                f0_ceil=f0_max,
+                f0_floor=f0_min,
+                frame_period=10,
+            )
+            f0 = pyworld.stonemask(x.astype(np.double), f0, t, self.sr)
+            f0 = signal.medfilt(f0, 3)
+
         f0 *= pow(2, f0_up_key / 12)
         tf0 = self.sr // self.window  # f0 points per second
         if inp_f0 is not None:
diff --git a/lib/rvc/preprocessing/extract_f0.py b/lib/rvc/preprocessing/extract_f0.py
@@ -4,7 +4,6 @@
 from typing import *
 
 import numpy as np
-import parselmouth
 import pyworld
 from tqdm import tqdm
 
@@ -21,24 +20,7 @@ def compute_f0(
 ):
     x = load_audio(path, fs)
     p_len = x.shape[0] // hop
-    if f0_method == "pm":
-        time_step = 160 / 16000 * 1000
-        f0_max = 1100
-        f0_min = 50
-        f0 = (
-            parselmouth.Sound(x, fs)
-            .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":
+    if f0_method == "harvest":
         f0, t = pyworld.harvest(
             x.astype(np.double),
             fs=fs,
diff --git a/requirements/main.txt b/requirements/main.txt
@@ -6,7 +6,6 @@ fairseq==0.12.2
 matplotlib==3.7.1
 scipy==1.9.3
 librosa==0.9.2
-praat-parselmouth==0.4.3
 pyworld==0.3.2
 soundfile==0.12.1
 ffmpeg-python==0.2.0
