fix: 移除多余 my_utils.py (#1189) (#1251)

* fix: 移除多余 my_utils.py (#1189)

* feat: update my_utils

GPT_SoVITS/inference_webui.py

@@ -65,7 +65,7 @@ from text import cleaned_text_to_sequence
 from text.cleaner import clean_text
 from time import time as ttime
 from module.mel_processing import spectrogram_torch
-from my_utils import load_audio
+from tools.my_utils import load_audio
 from tools.i18n.i18n import I18nAuto
 
 i18n = I18nAuto()

GPT_SoVITS/module/data_utils.py

@@ -17,7 +17,7 @@ from functools import lru_cache
 import requests
 from scipy.io import wavfile
 from io import BytesIO
-from my_utils import load_audio
+from tools.my_utils import load_audio
 
 # ZeroDivisionError fixed by Tybost (https://github.com/RVC-Boss/GPT-SoVITS/issues/79)
 class TextAudioSpeakerLoader(torch.utils.data.Dataset):

GPT_SoVITS/my_utils.py

@@ -1,21 +0,0 @@
-import ffmpeg
-import numpy as np
-
-
-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()

GPT_SoVITS/onnx_export.py

@@ -9,7 +9,7 @@ cnhubert.cnhubert_base_path=cnhubert_base_path
 ssl_model = cnhubert.get_model()
 from text import cleaned_text_to_sequence
 import soundfile
-from my_utils import load_audio
+from tools.my_utils import load_audio
 import os
 import json
 

GPT_SoVITS/prepare_datasets/2-get-hubert-wav32k.py

@@ -17,7 +17,7 @@ from scipy.io import wavfile
 import librosa,torch
 now_dir = os.getcwd()
 sys.path.append(now_dir)
-from my_utils import load_audio
+from tools.my_utils import load_audio
 
 # from config import cnhubert_base_path
 # cnhubert.cnhubert_base_path=cnhubert_base_path

api.py

@@ -143,7 +143,7 @@ from AR.models.t2s_lightning_module import Text2SemanticLightningModule
 from text import cleaned_text_to_sequence
 from text.cleaner import clean_text
 from module.mel_processing import spectrogram_torch
-from my_utils import load_audio
+from tools.my_utils import load_audio
 import config as global_config
 import logging
 import subprocess

tools/slice_audio.py

@@ -3,7 +3,7 @@ import traceback
 from scipy.io import wavfile
 # parent_directory = os.path.dirname(os.path.abspath(__file__))
 # sys.path.append(parent_directory)
-from my_utils import load_audio
+from tools.my_utils import load_audio
 from slicer2 import Slicer
 
 def slice(inp,opt_root,threshold,min_length,min_interval,hop_size,max_sil_kept,_max,alpha,i_part,all_part):