From 9ff976b155bee6651088caa71ffede3228effb97 Mon Sep 17 00:00:00 2001
From: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com>
Date: Tue, 6 Jun 2023 22:32:10 +0800
Subject: [PATCH] Add files via upload

---
 MDXNet.py     |  30 ++++++++++---
 infer-web.py  |  27 ++++++++---
 infer_uvr5.py | 122 +++++++++++++++++++++++++++++++++++++-------------
 3 files changed, 134 insertions(+), 45 deletions(-)

diff --git a/MDXNet.py b/MDXNet.py
index 7a1445a..d244f8a 100644
--- a/MDXNet.py
+++ b/MDXNet.py
@@ -86,7 +86,12 @@ def get_models(device, dim_f, dim_t, n_fft):
 
 warnings.filterwarnings("ignore")
 cpu = torch.device("cpu")
-device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+if torch.cuda.is_available():
+    device = torch.device("cuda:0")
+elif torch.backends.mps.is_available():
+    device = torch.device("mps")
+else:
+    device = torch.device("cpu")
 
 
 class Predictor:
@@ -201,11 +206,24 @@ class Predictor:
         mix = mix.T
         sources = self.demix(mix.T)
         opt = sources[0].T
-        sf.write(
-            "%s/%s_main_vocal.%s" % (vocal_root, basename, format), mix - opt, rate
-        )
-        sf.write("%s/%s_others.%s" % (others_root, basename, format), opt, rate)
-
+        if(format in ["wav", "flac"]):
+            sf.write("%s/%s_main_vocal.%s" % (vocal_root, basename, format), mix - opt, rate)
+            sf.write("%s/%s_others.%s" % (others_root, basename, format), opt, rate)
+        else:
+            path_vocal="%s/%s_main_vocal.wav" % (vocal_root, basename)
+            path_other="%s/%s_others.wav" % (others_root, basename)
+            sf.write(path_vocal, mix - opt, rate)
+            sf.write(path_other, opt, rate)
+            if (os.path.exists(path_vocal)):
+                os.system(
+                    "ffmpeg -i %s -vn %s -q:a 2 -y"
+                    % (path_vocal, path_vocal[:-4] + ".%s" % format)
+                )
+            if (os.path.exists(path_other)):
+                os.system(
+                    "ffmpeg -i %s -vn %s -q:a 2 -y"
+                    % (path_other, path_other[:-4] + ".%s" % format)
+                )
 
 class MDXNetDereverb:
     def __init__(self, chunks):
diff --git a/infer-web.py b/infer-web.py
index a9497ca..1d2f713 100644
--- a/infer-web.py
+++ b/infer-web.py
@@ -272,11 +272,24 @@ def vc_multi(
             if "Success" in info:
                 try:
                     tgt_sr, audio_opt = opt
-                    sf.write(
-                        "%s/%s.%s" % (opt_root, os.path.basename(path), format1),
-                        audio_opt,
-                        tgt_sr,
-                    )
+                    if (format1 in ["wav", "flac"]):
+                        sf.write(
+                            "%s/%s.%s" % (opt_root, os.path.basename(path), format1),
+                            audio_opt,
+                            tgt_sr,
+                        )
+                    else:
+                        path="%s/%s.wav" % (opt_root, os.path.basename(path))
+                        sf.write(
+                            path,
+                            audio_opt,
+                            tgt_sr,
+                        )
+                        if (os.path.exists(path)):
+                            os.system(
+                                "ffmpeg -i %s -vn %s -q:a 2 -y"
+                                % (path, path[:-4] + ".%s" % format1)
+                            )
                 except:
                     info += traceback.format_exc()
             infos.append("%s->%s" % (os.path.basename(path), info))
@@ -1400,8 +1413,8 @@ with gr.Blocks() as app:
                         "1、保留人声：不带和声的音频选这个，对主人声保留比HP5更好。内置HP2和HP3两个模型，HP3可能轻微漏伴奏但对主人声保留比HP2稍微好一丁点； <br>"
                         "2、仅保留主人声：带和声的音频选这个，对主人声可能有削弱。内置HP5一个模型； <br> "
                         "3、去混响、去延迟模型（by FoxJoy）：<br>"
-                        "  (1)MDX-Net:对于双通道混响是最好的选择，不能去除单通道混响；<br>"
-                        "        (234)DeEcho:去除延迟效果。Aggressive比Normal去除得更彻底，DeReverb额外去除混响，可去除单声道混响，但是对高频重的板式混响去不干净。<br>"
+                        "  (1)MDX-Net(onnx_dereverb):对于双通道混响是最好的选择，不能去除单通道混响；<br>"
+                        "&emsp;(234)DeEcho:去除延迟效果。Aggressive比Normal去除得更彻底，DeReverb额外去除混响，可去除单声道混响，但是对高频重的板式混响去不干净。<br>"
                         "去混响/去延迟，附：<br>"
                         "1、DeEcho-DeReverb模型的耗时是另外2个DeEcho模型的接近2倍；<br>"
                         "2、MDX-Net-Dereverb模型挺慢的；<br>"
diff --git a/infer_uvr5.py b/infer_uvr5.py
index c188c1a..bcbf78c 100644
--- a/infer_uvr5.py
+++ b/infer_uvr5.py
@@ -123,14 +123,29 @@ class _audio_pre_:
             else:
                 wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
             print("%s instruments done" % name)
-            sf.write(
-                os.path.join(
-                    ins_root,
-                    "instrument_{}_{}.{}".format(name, self.data["agg"], format),
-                ),
-                (np.array(wav_instrument) * 32768).astype("int16"),
-                self.mp.param["sr"],
-            )  #
+            if(format in ["wav","flac"]):
+                sf.write(
+                    os.path.join(
+                        ins_root,
+                        "instrument_{}_{}.{}".format(name, self.data["agg"], format),
+                    ),
+                    (np.array(wav_instrument) * 32768).astype("int16"),
+                    self.mp.param["sr"],
+                )  #
+            else:
+                path=os.path.join(
+                        ins_root, "instrument_{}_{}.wav".format(name, self.data["agg"])
+                    )
+                sf.write(
+                    path ,
+                    (np.array(wav_instrument) * 32768).astype("int16"),
+                    self.mp.param["sr"],
+                )
+                if(os.path.exists(path)):
+                    os.system(
+                        "ffmpeg -i %s -vn %s -q:a 2 -y"
+                        % (path, path[:-4]+".%s"%format)
+                    )
         if vocal_root is not None:
             if self.data["high_end_process"].startswith("mirroring"):
                 input_high_end_ = spec_utils.mirroring(
@@ -142,14 +157,28 @@ class _audio_pre_:
             else:
                 wav_vocals = spec_utils.cmb_spectrogram_to_wave(v_spec_m, self.mp)
             print("%s vocals done" % name)
-            sf.write(
-                os.path.join(
-                    vocal_root, "vocal_{}_{}.{}".format(name, self.data["agg"], format)
-                ),
-                (np.array(wav_vocals) * 32768).astype("int16"),
-                self.mp.param["sr"],
-            )
-
+            if(format in ["wav","flac"]):
+                sf.write(
+                    os.path.join(
+                        vocal_root, "vocal_{}_{}.{}".format(name, self.data["agg"], format)
+                    ),
+                    (np.array(wav_vocals) * 32768).astype("int16"),
+                    self.mp.param["sr"],
+                )
+            else:
+                path=os.path.join(
+                        vocal_root, "vocal_{}_{}.wav".format(name, self.data["agg"])
+                    )
+                sf.write(
+                    path ,
+                    (np.array(wav_vocals) * 32768).astype("int16"),
+                    self.mp.param["sr"],
+                )
+                if(os.path.exists(path)):
+                    os.system(
+                        "ffmpeg -i %s -vn %s -q:a 2 -y"
+                        % (path, path[:-4]+".%s"%format)
+                    )
 
 class _audio_pre_new:
     def __init__(self, agg, model_path, device, is_half):
@@ -259,14 +288,29 @@ class _audio_pre_new:
             else:
                 wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
             print("%s instruments done" % name)
-            sf.write(
-                os.path.join(
-                    ins_root,
-                    "main_vocal_{}_{}.{}".format(name, self.data["agg"], format),
-                ),
-                (np.array(wav_instrument) * 32768).astype("int16"),
-                self.mp.param["sr"],
-            )  #
+            if(format in ["wav","flac"]):
+                sf.write(
+                    os.path.join(
+                        ins_root,
+                        "instrument_{}_{}.{}".format(name, self.data["agg"], format),
+                    ),
+                    (np.array(wav_instrument) * 32768).astype("int16"),
+                    self.mp.param["sr"],
+                )  #
+            else:
+                path=os.path.join(
+                        ins_root, "instrument_{}_{}.wav".format(name, self.data["agg"])
+                    )
+                sf.write(
+                    path ,
+                    (np.array(wav_instrument) * 32768).astype("int16"),
+                    self.mp.param["sr"],
+                )
+                if(os.path.exists(path)):
+                    os.system(
+                        "ffmpeg -i %s -vn %s -q:a 2 -y"
+                        % (path, path[:-4]+".%s"%format)
+                    )
         if vocal_root is not None:
             if self.data["high_end_process"].startswith("mirroring"):
                 input_high_end_ = spec_utils.mirroring(
@@ -278,14 +322,28 @@ class _audio_pre_new:
             else:
                 wav_vocals = spec_utils.cmb_spectrogram_to_wave(v_spec_m, self.mp)
             print("%s vocals done" % name)
-            sf.write(
-                os.path.join(
-                    vocal_root, "others_{}_{}.{}".format(name, self.data["agg"], format)
-                ),
-                (np.array(wav_vocals) * 32768).astype("int16"),
-                self.mp.param["sr"],
-            )
-
+            if(format in ["wav","flac"]):
+                sf.write(
+                    os.path.join(
+                        vocal_root, "vocal_{}_{}.{}".format(name, self.data["agg"], format)
+                    ),
+                    (np.array(wav_vocals) * 32768).astype("int16"),
+                    self.mp.param["sr"],
+                )
+            else:
+                path=os.path.join(
+                        vocal_root, "vocal_{}_{}.wav".format(name, self.data["agg"])
+                    )
+                sf.write(
+                    path ,
+                    (np.array(wav_vocals) * 32768).astype("int16"),
+                    self.mp.param["sr"],
+                )
+                if(os.path.exists(path)):
+                    os.system(
+                        "ffmpeg -i %s -vn %s -q:a 2 -y"
+                        % (path, path[:-4]+".%s"%format)
+                    )
 
 if __name__ == "__main__":
     device = "cuda"