Tweaked files upload and replace

formanting.txt

@@ -0,0 +1,3 @@
+False
+8.0
+1.2

formantshiftcfg/f2m.txt

@@ -0,0 +1,2 @@
+8.0
+-1.2

formantshiftcfg/m2f.txt

@@ -0,0 +1,2 @@
+8.0
+1.2

formantshiftcfg/random.txt

@@ -0,0 +1,2 @@
+16.0
+9.8

installstft.bat

@@ -0,0 +1,6 @@
+runtime\python.exe -m pip install stftpitchshift --upgrade
+runtime\python.exe -m pip install gradio==3.34.0 --upgrade
+
+
+IF EXIST ".\rmvpe.pt" (echo RMVPE is already installed) ELSE (bitsadmin /transfer "rvmpedwnld" /download /priority FOREGROUND "https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt" "%~dp0rmvpe.pt")
+pause

my_utils.py

@@ -1,8 +1,13 @@
 import ffmpeg
 import numpy as np
+#import praatio
+#import praatio.praat_scripts
+import os
+#from os.path import join
 
+#praatEXE = join('.',os.path.abspath(os.getcwd()) + r"\Praat.exe")
 
-def load_audio(file, sr):
+def load_audio(file, sr, DoFormant, Quefrency, Timbre):
     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.
@@ -10,11 +15,44 @@ def load_audio(file, sr):
         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)
+        file_formanted = (
+            file.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
         )
+        with open('formanting.txt', 'r') as fvf:
+            content = fvf.readlines()
+            if 'True' in content[0].split('\n')[0]:
+                #print("true")
+                DoFormant = True
+                Quefrency, Timbre = content[1].split('\n')[0], content[2].split('\n')[0]
+                
+            else:
+                #print("not true")
+                DoFormant = False
+            
+        if DoFormant:
+            #os.system(f"stftpitchshift -i {file} -q {Quefrency} -t {Timbre} -o {file_formanted}")
+            #print('stftpitchshift -i "%s" -p 1.0 --rms -w 128 -v 8 -q %s -t %s -o "%s"' % (file, Quefrency, Timbre, file_formanted))
+            print("formanting...")
+            
+            os.system('stftpitchshift -i "%s" -q %s -t %s -o "%sFORMANTED"' % (file, Quefrency, Timbre, file_formanted))
+            print("formanted!")
+            #filepraat = (os.path.abspath(os.getcwd()) + '\\' + file).replace('/','\\')
+            #file_formantedpraat = ('"' + os.path.abspath(os.getcwd()) + '/' + 'formanted'.join(file_formanted) + '"').replace('/','\\')
+
+            out, _ = (
+                ffmpeg.input('%sFORMANTED%s' % (file_formanted, '.wav'), threads=0)
+                .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
+                .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
+            )
+            
+            os.remove('%sFORMANTED%s' % (file_formanted, '.wav'))
+        else:
+            
+            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}")