somefix vc

infer/modules/vc/modules.py

@@ -1,5 +1,6 @@
 import traceback
 
+import numpy as np
 import torch
 import soundfile as sf
 
@@ -11,6 +12,7 @@ from infer.lib.infer_pack.models import (
 )
 from infer.modules.vc.pipeline import Pipeline
 from infer.modules.vc.utils import *
+from infer.lib.audio import load_audio
 
 
 class VC:

infer/modules/vc/utils.py

@@ -1,7 +1,5 @@
 import os
 
-import numpy as np
-import ffmpeg
 from fairseq import checkpoint_utils
 
 
@@ -34,21 +32,3 @@ def load_hubert(config):
         hubert_model = hubert_model.float()
     return hubert_model.eval()
 
-
-def load_audio(file, sr):
-    try:
-        # https://github.com/openai/whisper/blob/main/whisper/audio.py#L26
-        # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
-        # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
-        file = (
-            file.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
-        )  # 防止小白拷路径头尾带了空格和"和回车
-        out, _ = (
-            ffmpeg.input(file, threads=0)
-            .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
-            .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
-        )
-    except Exception as e:
-        raise RuntimeError(f"Failed to load audio: {e}")
-
-    return np.frombuffer(out, np.float32).flatten()