Create app.py

app.py

@@ -0,0 +1,60 @@
+import io
+import os
+
+# os.system("wget -P cvec/ https://huggingface.co/spaces/innnky/nanami/resolve/main/checkpoint_best_legacy_500.pt")
+import gradio as gr
+import librosa
+import numpy as np
+import soundfile
+from inference.infer_tool import Svc
+import logging
+
+logging.getLogger('numba').setLevel(logging.WARNING)
+logging.getLogger('markdown_it').setLevel(logging.WARNING)
+logging.getLogger('urllib3').setLevel(logging.WARNING)
+logging.getLogger('matplotlib').setLevel(logging.WARNING)
+
+config_path = "config.json"
+
+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(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)
+    return "Success", (44100, _audio)
+
+
+app = gr.Blocks()
+with app:
+    with gr.Tabs():
+        with gr.TabItem("Basic"):
+            gr.Markdown(value="""
+                sovits4.0 Arknights
+                自练模型，内有 伊芙利特 凯尔希 桃金娘 塞雷娅 斯卡蒂
+                """)
+            spks = list(model.spk2id.keys())
+            vc_input3 = gr.Audio(label="上传音频（长度小于90秒）")
+            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])
+
+    app.launch()