Update app.py

app.py

@@ -21,7 +21,50 @@ model = Svc("G_754.pth", "config.json")
 # model = Svc("E:/Items/so-vits-svc/models/Arknights/G_10400.pth", "E:/Items/so-vits-svc/models/Arknights/config.json")
 
 
-def vc_fn(sid,input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale):
+# def vc_fn(sid,input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale):
+#     if input_audio is None:
+#         return "You need to upload an audio", None
+#     sampling_rate, audio = input_audio
+#     # print(audio.shape,sampling_rate)
+#     duration = audio.shape[0] / sampling_rate
+#     if duration > 90:
+#         return "请上传小于90s的音频，需要转换长音频请本地进行转换", None
+#     audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
+#     if len(audio.shape) > 1:
+#         audio = librosa.to_mono(audio.transpose(1, 0))
+#     # if sampling_rate != 16000:
+#     #     audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
+#     print(audio.shape)
+#     out_wav_path = "temp.wav"
+#     soundfile.write(out_wav_path, audio, 16000, format="wav")
+#     # print( cluster_ratio, auto_f0, noise_scale)
+#     _audio = model.slice_inference(out_wav_path,sid, vc_transform, slice_db, cluster_ratio, auto_f0, noise_scale)
+#     return "Success", (44100, _audio)
+
+
+# app = gr.Blocks()
+# with app:
+#     with gr.Tabs():
+#         with gr.TabItem("Basic"):
+#             gr.Markdown(value="""
+#                 sovits Ameli
+#                 Upload your audio
+#                 """)
+#             spks = list(model.spk2id.keys())
+#             # sid = gr.Dropdown(label="Voice Tone", choices=spks, value=spks[0])
+#             vc_input3 = gr.Audio(label="Upload your audio(under 90s length)")
+#             vc_submit = gr.Button("Run", variant="primary")
+#             vc_output1 = gr.Textbox(label="Output Message")
+#             vc_output2 = gr.Audio(label="Output Audio")
+#         vc_submit.click(vc_fn, [vc_input3], [vc_output1, vc_output2])
+#         # vc_submit.click(vc_fn, [vc_input3,0,-40,0,False,0.4], [vc_output1, vc_output2])
+
+#     app.launch()
+
+
+
+
+def vc_fn(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale):
     if input_audio is None:
         return "You need to upload an audio", None
     sampling_rate, audio = input_audio
@@ -32,13 +75,13 @@ def vc_fn(sid,input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_
     audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
     if len(audio.shape) > 1:
         audio = librosa.to_mono(audio.transpose(1, 0))
-    # if sampling_rate != 16000:
-    #     audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
+    if sampling_rate != 16000:
+        audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
     print(audio.shape)
     out_wav_path = "temp.wav"
     soundfile.write(out_wav_path, audio, 16000, format="wav")
-    # print( cluster_ratio, auto_f0, noise_scale)
-    _audio = model.slice_inference(out_wav_path,sid, vc_transform, slice_db, cluster_ratio, auto_f0, noise_scale)
+    print( cluster_ratio, auto_f0, noise_scale)
+    _audio = model.slice_inference(out_wav_path, sid, vc_transform, slice_db, cluster_ratio, auto_f0, noise_scale)
     return "Success", (44100, _audio)
 
 
@@ -51,13 +94,16 @@ with app:
                 Upload your audio
                 """)
             spks = list(model.spk2id.keys())
-            # sid = gr.Dropdown(label="Voice Tone", choices=spks, value=spks[0])
-            vc_input3 = gr.Audio(label="Upload your audio(under 90s length)")
-            vc_submit = gr.Button("Run", variant="primary")
+            sid = gr.Dropdown(label="音色", choices=spks, value=spks[0])
+            vc_input3 = gr.Audio(label="上传音频（长度小于90秒）")
+            vc_transform = gr.Number(label="变调（整数，可以正负，半音数量，升高八度就是12）", value=0)
+            cluster_ratio = gr.Number(label="聚类模型混合比例，0-1之间，默认为0不启用聚类，能提升音色相似度，但会导致咬字下降（如果使用建议0.5左右）", value=0)
+            auto_f0 = gr.Checkbox(label="自动f0预测，配合聚类模型f0预测效果更好,会导致变调功能失效（仅限转换语音，歌声不要勾选此项会究极跑调）", value=False)
+            slice_db = gr.Number(label="切片阈值", value=-40)
+            noise_scale = gr.Number(label="noise_scale 建议不要动，会影响音质，玄学参数", value=0.4)
+            vc_submit = gr.Button("转换", variant="primary")
             vc_output1 = gr.Textbox(label="Output Message")
             vc_output2 = gr.Audio(label="Output Audio")
-        vc_submit.click(vc_fn, [vc_input3], [vc_output1, vc_output2])
-        # vc_submit.click(vc_fn, [vc_input3,0,-40,0,False,0.4], [vc_output1, vc_output2])
-
-    app.launch()
+        vc_submit.click(vc_fn, [sid, vc_input3, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale], [vc_output1, vc_output2])
 
+    app.launch()