COM

app.py

@@ -39,6 +39,8 @@ debug = False
 sovits_params = {}
 diff_params = {}
 
+loaded = None
+
 def debug_change():
     global debug
     debug = debug_button.value
@@ -140,6 +142,43 @@ def load_model_func(ckpt_name,cluster_name,config_name,enhance,diff_model_name,d
     output_msg = f"模型被成功加载到了{device_name}上\n{index_or_kmeans}：{clu_load}\n扩散模型：{diff_load}"
     return output_msg, gr.Dropdown.update(choices=spk_list, value=spk_choice), clip
 
+def Newload_model_func(ckpt_name,cluster_name,config_name,enhance,diff_model_name,diff_config_name,only_diffusion,encoder,using_device):
+    global model
+    config_path = os.path.join(config_dir, config_name)
+    diff_config_path = os.path.join(config_dir, diff_config_name) if diff_config_name != "no_diff_config" else "configs/diffusion.yaml"
+    with open(config_path, 'r') as f:
+        config = json.load(f)
+    spk_dict = config["spk"]
+    spk_name = config.get('spk', None)
+    spk_choice = next(iter(spk_name)) if spk_name else "未检测到音色"
+    ckpt_path = os.path.join(workdir, ckpt_name)
+    _, _suffix = os.path.splitext(cluster_name)
+    fr = True if _suffix == ".pkl" else False #如果是pkl后缀就启用特征检索
+    cluster_path = os.path.join(workdir, cluster_name)
+    diff_model_path = os.path.join(diff_workdir, diff_model_name)
+    shallow_diffusion = True if diff_model_name != "no_diff" else False
+    use_spk_mix = False
+    device = None if using_device == "Auto" else using_device
+    model = Svc(ckpt_path,
+                    config_path,
+                    device,
+                    cluster_path,
+                    enhance,
+                    diff_model_path,
+                    diff_config_path,
+                    shallow_diffusion,
+                    only_diffusion,
+                    use_spk_mix,
+                    fr)
+    spk_list = list(spk_dict.keys())
+    clip = 25 if encoder == "Whisper-PPG" else 0 #Whisper必须强制切片25秒
+    device_name = torch.cuda.get_device_properties(model.dev).name if "cuda" in str(model.dev) else str(model.dev)
+    index_or_kmeans = "特征索引" if fr is True else "聚类模型"
+    clu_load = "未加载" if cluster_name == "no_clu" else cluster_name
+    diff_load = "未加载" if diff_model_name == "no_diff" else diff_model_name
+    #output_msg = f"模型被成功加载到了{device_name}上\n{index_or_kmeans}：{clu_load}\n扩散模型：{diff_load}"
+    #return output_msg, gr.Dropdown.update(choices=spk_list, value=spk_choice), clip
+
 def get_file_options(directory, extension):
     return [file for file in os.listdir(directory) if file.endswith(extension)]
 
@@ -662,6 +701,21 @@ gpus="-".join([i[0]for i in gpu_infos])
 sovits_params, diff_params = get_default_settings()
 
 app = gr.Blocks()
+
+def Newget_model_info(choice_ckpt):
+    pthfile = os.path.join(workdir, choice_ckpt)
+    net = torch.load(pthfile, map_location=torch.device('cpu')) #cpu load
+    spk_emb = net["model"].get("emb_g.weight")
+    if spk_emb is None:
+        return "所选模型缺少emb_g.weight，你可能选择了一个底模"
+    _dim, _layer = spk_emb.size()
+    model_type = {
+        768: "Vec768-Layer12",
+        256: "Vec256-Layer9 / HubertSoft",
+        1024: "Whisper-PPG"
+    }
+    return gr.Textbox(visible=False, value=model_type.get(_layer, "不受支持的模型"))
+
 with app:
     gr.Markdown(value="""
         ### So-VITS-SVC 4.1-Stable
@@ -677,30 +731,39 @@ with app:
         """)
     with gr.Tabs():
         with gr.TabItem("推理"):
+            #with gr.Row():
+            #    choice_ckpt = gr.Dropdown(label="模型选择", choices=ckpt_list, value="no_model")
+            #    model_branch = gr.Textbox(label="模型编码器", placeholder="请先选择模型", interactive=False)
+            choice_ckpt = gr.Dropdown(value="G_82400.pth", visible=False)
+            #with gr.Row():
+            #    config_choice = gr.Dropdown(label="配置文件", choices=config_list, value="no_config")
+            #    config_info = gr.Textbox(label="配置文件编码器", placeholder="请选择配置文件")
+            config_choice = gr.Dropdown(value="config.json", visible=False)
+            #gr.Markdown(value="""**请检查模型和配置文件的编码器是否匹配**""")
+            #with gr.Row():
+            #    diff_choice = gr.Dropdown(label="（可选）选择扩散模型", choices=diff_list, value="no_diff", interactive=True)
+            #    diff_config_choice = gr.Dropdown(label="扩散模型配置文件", choices=diff_config_list, value="no_diff_config", interactive=True)
+            diff_choice = gr.Dropdown(value="no_diff", visible=False)
+            diff_config_choice = gr.Dropdown(value="no_diff_config", visible=False)
             with gr.Row():
-                choice_ckpt = gr.Dropdown(label="模型选择", choices=ckpt_list, value="no_model")
-                model_branch = gr.Textbox(label="模型编码器", placeholder="请先选择模型", interactive=False)
-            with gr.Row():
-                config_choice = gr.Dropdown(label="配置文件", choices=config_list, value="no_config")
-                config_info = gr.Textbox(label="配置文件编码器", placeholder="请选择配置文件")
-            gr.Markdown(value="""**请检查模型和配置文件的编码器是否匹配**""")
-            with gr.Row():
-                diff_choice = gr.Dropdown(label="（可选）选择扩散模型", choices=diff_list, value="no_diff", interactive=True)
-                diff_config_choice = gr.Dropdown(label="扩散模型配置文件", choices=diff_config_list, value="no_diff_config", interactive=True)
-            cluster_choice = gr.Dropdown(label="（可选）选择聚类模型/特征检索模型", choices=cluster_list, value="no_clu")
+                cluster_choice = gr.Dropdown(label="（可选）选择聚类模型/特征检索模型", choices=cluster_list, value="no_clu")
             with gr.Row():
                 enhance = gr.Checkbox(label="是否使用NSF_HIFIGAN增强，该选项对部分训练集少的模型有一定的音质增强效果，但是对训练好的模型有反面效果，默认关闭", value=False)
-                only_diffusion = gr.Checkbox(label="是否使用全扩散推理，开启后将不使用So-VITS模型，仅使用扩散模型进行完整扩散推理，默认关闭", value=False)
-            using_device = gr.Dropdown(label="推理设备，默认为自动选择", choices=["Auto","cuda","cpu"], value="Auto")
-            refresh = gr.Button("刷新选项")
-            loadckpt = gr.Button("加载模型", variant="primary")
-            with gr.Row():
-                model_message = gr.Textbox(label="Output Message")
-                sid = gr.Dropdown(label="So-VITS说话人", value="speaker0")
+                #only_diffusion = gr.Checkbox(label="是否使用全扩散推理，开启后将不使用So-VITS模型，仅使用扩散模型进行完整扩散推理，默认关闭", value=False)
+                only_diffusion = gr.Checkbox(value=False, visible=False)
+            #using_device = gr.Dropdown(label="推理设备，默认为自动选择", choices=["Auto","cuda","cpu"], value="Auto")
+            using_device = gr.Dropdown(value='Auto', visible=False)
+            #refresh = gr.Button("刷新选项")
+            #loadckpt = gr.Button("加载模型", variant="primary")
+            #with gr.Row():
+            #    model_message = gr.Textbox(label="Output Message")
+            #    sid = gr.Dropdown(label="So-VITS说话人", value="speaker0")
+            sid = gr.Dropdown(value="1001", visible=False)
             
-            choice_ckpt.change(get_model_info, [choice_ckpt], [model_branch])  
-            config_choice.change(load_json_encoder, [config_choice], [config_info])
-            refresh.click(refresh_options,[],[choice_ckpt,config_choice,cluster_choice,diff_choice,diff_config_choice])
+            #choice_ckpt.change(get_model_info, [choice_ckpt], [model_branch])
+            model_branch = Newget_model_info(choice_ckpt)
+            #config_choice.change(load_json_encoder, [config_choice], [config_info])
+            #refresh.click(refresh_options,[],[choice_ckpt,config_choice,cluster_choice,diff_choice,diff_config_choice])
 
             gr.Markdown(value="""
                 请稍等片刻，模型加载大约需要10秒。后续操作不需要重新加载模型
@@ -756,7 +819,8 @@ with app:
             vc_output1 = gr.Textbox(label="Output Message")
             vc_output2 = gr.Audio(label="Output Audio")
         
-        loadckpt.click(load_model_func,[choice_ckpt,cluster_choice,config_choice,enhance,diff_choice,diff_config_choice,only_diffusion,model_branch,using_device],[model_message, sid, cl_num])
+        #loadckpt.click(load_model_func,[choice_ckpt,cluster_choice,config_choice,enhance,diff_choice,diff_config_choice,only_diffusion,model_branch,using_device],[model_message, sid, cl_num])
+        Newload_model_func(choice_ckpt,cluster_choice,config_choice,enhance,diff_choice,diff_config_choice,only_diffusion,model_branch,using_device)
         vc_submit.click(vc_fn, [sid, vc_input3, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,f0_predictor,enhancer_adaptive_key,cr_threshold,k_step,use_spk_mix,second_encoding,loudness_envelope_adjustment], [vc_output1, vc_output2])
         vc_batch_submit.click(vc_batch_fn, [sid, vc_batch_files, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,f0_predictor,enhancer_adaptive_key,cr_threshold,k_step,use_spk_mix,second_encoding,loudness_envelope_adjustment], [vc_output1])
         vc_tts_submit.click(tts_fn, [text_input, tts_spk, sid, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,f0_predictor,enhancer_adaptive_key,cr_threshold,k_step,use_spk_mix,second_encoding,loudness_envelope_adjustment], [vc_output1, vc_output2])