Update app.py

app.py

@@ -71,18 +71,16 @@ def load(speaker):
     global model
     sid = speaker
     model = Svc(models_info[sid]["model"], models_info[sid]["config"], cluster_model_path=models_info[sid]["cluster"], feature_retrieval=models_info[sid]["feature_retrieval"])
-    return "加载成功", sid
-load(speakers[0])
+    return "Model loaded successfully", sid
+sid = speakers[0]
+load(sid)
 
 def vc_fn(input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale):
     global sid
     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))
@@ -98,18 +96,19 @@ def vc_fn(input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scal
 app = gr.Blocks()
 with app:
     with gr.Tabs():
-        with gr.TabItem("推理"):
-            speaker = gr.Dropdown(label="讲话人", choices=speakers, value=speakers[0])
-            model_submit = gr.Button("加载模型", variant="primary")
+        with gr.TabItem("Inference"):
+            speaker = gr.Dropdown(label="Speaker", choices=speakers, value=speakers[0])
+            model_submit = gr.Button("Load Model", variant="primary")
             model_output1 = gr.Textbox(label="Output Message")
-            model_output2 = gr.Textbox(label="Output Message", value=sid)
-            vc_input3 = gr.Audio(label="上传音频")
-            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")
+            load(sid)
+            model_output2 = gr.Textbox(label="Speaker", value=sid)
+            vc_input3 = gr.Audio(label="Upload Audio")
+            vc_transform = gr.Number(label="Pitch Shift (integer, can be positive or negative, number of semitones, raising an octave is +12)", value=0)
+            cluster_ratio = gr.Number(label="Cluster Model Mixing Ratio (0-1): Defaults to 0 (clustering disabled). Improves timbre similarity but may reduce articulation clarity. Recommended value: ~0.5 if used", value=0)
+            auto_f0 = gr.Checkbox(label="Auto f0 Prediction: Works better with the cluster model for f0 prediction but disables the pitch shift feature. (For voice conversion only; do not enable this for singing voices, as it will result in extreme off-pitch issues)", value=False)
+            slice_db = gr.Number(label="Slicing Threshold", value=-40)
+            noise_scale = gr.Number(label="noise_scale", value=0.4)
+            vc_submit = gr.Button("Convert", variant="primary")
             vc_output1 = gr.Textbox(label="Output Message")
             vc_output2 = gr.Audio(label="Output Audio")
         model_submit.click(load, [speaker], [model_output1, model_output2])