commit update

.vs/OpenVoice/v17/DocumentLayout.json

@@ -0,0 +1,105 @@
+{
+  "Version": 1,
+  "WorkspaceRootPath": "C:\\Users\\spsee\\OpenVoice\\",
+  "Documents": [
+    {
+      "AbsoluteMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|C:\\Users\\spsee\\OpenVoice\\requirements.txt||{8B382828-6202-11D1-8870-0000F87579D2}",
+      "RelativeMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|solutionrelative:requirements.txt||{8B382828-6202-11D1-8870-0000F87579D2}"
+    },
+    {
+      "AbsoluteMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|C:\\Users\\spsee\\OpenVoice\\openvoice\\openvoice_app.py||{8B382828-6202-11D1-8870-0000F87579D2}",
+      "RelativeMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|solutionrelative:openvoice\\openvoice_app.py||{8B382828-6202-11D1-8870-0000F87579D2}"
+    },
+    {
+      "AbsoluteMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|C:\\Users\\spsee\\OpenVoice\\openvoice\\api.py||{8B382828-6202-11D1-8870-0000F87579D2}",
+      "RelativeMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|solutionrelative:openvoice\\api.py||{8B382828-6202-11D1-8870-0000F87579D2}"
+    },
+    {
+      "AbsoluteMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|C:\\Users\\spsee\\OpenVoice\\demo_part3.ipynb||{90A6B3A7-C1A3-4009-A288-E2FF89E96FA0}",
+      "RelativeMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|solutionrelative:demo_part3.ipynb||{90A6B3A7-C1A3-4009-A288-E2FF89E96FA0}"
+    },
+    {
+      "AbsoluteMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|C:\\Users\\spsee\\OpenVoice\\setup.py||{8B382828-6202-11D1-8870-0000F87579D2}",
+      "RelativeMoniker": "D:0:0:{A2FE74E1-B743-11D0-AE1A-00A0C90FFFC3}|\u003CMiscFiles\u003E|solutionrelative:setup.py||{8B382828-6202-11D1-8870-0000F87579D2}"
+    }
+  ],
+  "DocumentGroupContainers": [
+    {
+      "Orientation": 0,
+      "VerticalTabListWidth": 256,
+      "DocumentGroups": [
+        {
+          "DockedWidth": 200,
+          "SelectedChildIndex": 0,
+          "Children": [
+            {
+              "$type": "Document",
+              "DocumentIndex": 0,
+              "Title": "requirements.txt",
+              "DocumentMoniker": "C:\\Users\\spsee\\OpenVoice\\requirements.txt",
+              "RelativeDocumentMoniker": "requirements.txt",
+              "ToolTip": "C:\\Users\\spsee\\OpenVoice\\requirements.txt",
+              "RelativeToolTip": "requirements.txt",
+              "ViewState": "AQIAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
+              "Icon": "ae27a6b0-e345-4288-96df-5eaf394ee369.003109|",
+              "WhenOpened": "2024-05-29T06:00:53.88Z",
+              "EditorCaption": ""
+            },
+            {
+              "$type": "Document",
+              "DocumentIndex": 1,
+              "Title": "openvoice_app.py",
+              "DocumentMoniker": "C:\\Users\\spsee\\OpenVoice\\openvoice\\openvoice_app.py",
+              "RelativeDocumentMoniker": "openvoice\\openvoice_app.py",
+              "ToolTip": "C:\\Users\\spsee\\OpenVoice\\openvoice\\openvoice_app.py",
+              "RelativeToolTip": "openvoice\\openvoice_app.py",
+              "ViewState": "AQIAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
+              "Icon": "ae27a6b0-e345-4288-96df-5eaf394ee369.002457|",
+              "WhenOpened": "2024-05-29T05:43:03.287Z",
+              "EditorCaption": ""
+            },
+            {
+              "$type": "Document",
+              "DocumentIndex": 2,
+              "Title": "api.py",
+              "DocumentMoniker": "C:\\Users\\spsee\\OpenVoice\\openvoice\\api.py",
+              "RelativeDocumentMoniker": "openvoice\\api.py",
+              "ToolTip": "C:\\Users\\spsee\\OpenVoice\\openvoice\\api.py",
+              "RelativeToolTip": "openvoice\\api.py",
+              "ViewState": "AQIAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
+              "Icon": "ae27a6b0-e345-4288-96df-5eaf394ee369.002457|",
+              "WhenOpened": "2024-05-29T05:42:57.701Z",
+              "EditorCaption": ""
+            },
+            {
+              "$type": "Document",
+              "DocumentIndex": 3,
+              "Title": "demo_part3.ipynb",
+              "DocumentMoniker": "C:\\Users\\spsee\\OpenVoice\\demo_part3.ipynb",
+              "RelativeDocumentMoniker": "demo_part3.ipynb",
+              "ToolTip": "C:\\Users\\spsee\\OpenVoice\\demo_part3.ipynb",
+              "RelativeToolTip": "demo_part3.ipynb",
+              "ViewState": "AQIAAF0AAAAAAAAAAAAAAAAAAAAAAAAA",
+              "Icon": "ae27a6b0-e345-4288-96df-5eaf394ee369.001001|",
+              "WhenOpened": "2024-05-29T05:42:22.624Z",
+              "EditorCaption": ""
+            },
+            {
+              "$type": "Document",
+              "DocumentIndex": 4,
+              "Title": "setup.py",
+              "DocumentMoniker": "C:\\Users\\spsee\\OpenVoice\\setup.py",
+              "RelativeDocumentMoniker": "setup.py",
+              "ToolTip": "C:\\Users\\spsee\\OpenVoice\\setup.py",
+              "RelativeToolTip": "setup.py",
+              "ViewState": "AQIAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
+              "Icon": "ae27a6b0-e345-4288-96df-5eaf394ee369.002457|",
+              "WhenOpened": "2024-05-29T04:20:21.828Z",
+              "EditorCaption": ""
+            }
+          ]
+        }
+      ]
+    }
+  ]
+}

.vs/ProjectSettings.json

@@ -0,0 +1,3 @@
+{
+  "CurrentProjectSetting": null
+}

.vs/PythonSettings.json

@@ -0,0 +1,3 @@
+{
+  "Interpreter": "env\\Scripts\\python.exe"
+}

.vs/VSWorkspaceState.json

@@ -0,0 +1,10 @@
+{
+  "ActiveTargetSystem": "WSL: Ubuntu",
+  "ExpandedNodes": [
+    "",
+    "\\openvoice",
+    "\\openvoice\\text"
+  ],
+  "SelectedNode": "\\requirements.txt",
+  "PreviewInSolutionExplorer": false
+}

demo_part1.ipynb

@@ -10,10 +10,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "b7f043ee",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'torch'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[2], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mos\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mopenvoice\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m se_extractor\n\u001b[0;32m      4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mopenvoice\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mapi\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BaseSpeakerTTS, ToneColorConverter\n",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'torch'"
+     ]
+    }
+   ],
    "source": [
     "import os\n",
     "import torch\n",
@@ -31,10 +43,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "aacad912",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'torch' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[3], line 3\u001b[0m\n\u001b[0;32m      1\u001b[0m ckpt_base \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcheckpoints/base_speakers/EN\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m      2\u001b[0m ckpt_converter \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcheckpoints/converter\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m----> 3\u001b[0m device\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcuda:0\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mis_available() \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcpu\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m      4\u001b[0m output_dir \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124moutputs\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m      6\u001b[0m base_speaker_tts \u001b[38;5;241m=\u001b[39m BaseSpeakerTTS(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mckpt_base\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/config.json\u001b[39m\u001b[38;5;124m'\u001b[39m, device\u001b[38;5;241m=\u001b[39mdevice)\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'torch' is not defined"
+     ]
+    }
+   ],
    "source": [
     "ckpt_base = 'checkpoints/base_speakers/EN'\n",
     "ckpt_converter = 'checkpoints/converter'\n",
@@ -70,10 +94,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "63ff6273",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'torch' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[4], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m source_se \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mload(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mckpt_base\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/en_default_se.pth\u001b[39m\u001b[38;5;124m'\u001b[39m)\u001b[38;5;241m.\u001b[39mto(device)\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'torch' is not defined"
+     ]
+    }
+   ],
    "source": [
     "source_se = torch.load(f'{ckpt_base}/en_default_se.pth').to(device)"
    ]
@@ -88,10 +124,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "55105eae",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'se_extractor' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[5], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m reference_speaker \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mresources/example_reference.mp3\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;66;03m# This is the voice you want to clone\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m target_se, audio_name \u001b[38;5;241m=\u001b[39m se_extractor\u001b[38;5;241m.\u001b[39mget_se(reference_speaker, tone_color_converter, target_dir\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mprocessed\u001b[39m\u001b[38;5;124m'\u001b[39m, vad\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'se_extractor' is not defined"
+     ]
+    }
+   ],
    "source": [
     "reference_speaker = 'resources/example_reference.mp3' # This is the voice you want to clone\n",
     "target_se, audio_name = se_extractor.get_se(reference_speaker, tone_color_converter, target_dir='processed', vad=True)"
@@ -107,10 +155,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "73dc1259",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'output_dir' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[6], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m save_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00moutput_dir\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/output_en_default.wav\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m      3\u001b[0m \u001b[38;5;66;03m# Run the base speaker tts\u001b[39;00m\n\u001b[0;32m      4\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThis audio is generated by OpenVoice.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'output_dir' is not defined"
+     ]
+    }
+   ],
    "source": [
     "save_path = f'{output_dir}/output_en_default.wav'\n",
     "\n",
@@ -139,10 +199,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "id": "fd022d38",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'torch' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[7], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m source_se \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mload(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mckpt_base\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/en_style_se.pth\u001b[39m\u001b[38;5;124m'\u001b[39m)\u001b[38;5;241m.\u001b[39mto(device)\n\u001b[0;32m      2\u001b[0m save_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00moutput_dir\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/output_whispering.wav\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m      4\u001b[0m \u001b[38;5;66;03m# Run the base speaker tts\u001b[39;00m\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'torch' is not defined"
+     ]
+    }
+   ],
    "source": [
     "source_se = torch.load(f'{ckpt_base}/en_style_se.pth').to(device)\n",
     "save_path = f'{output_dir}/output_whispering.wav'\n",
@@ -172,10 +244,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "a71d1387",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'BaseSpeakerTTS' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[8], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m ckpt_base \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcheckpoints/base_speakers/ZH\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m----> 2\u001b[0m base_speaker_tts \u001b[38;5;241m=\u001b[39m BaseSpeakerTTS(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mckpt_base\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/config.json\u001b[39m\u001b[38;5;124m'\u001b[39m, device\u001b[38;5;241m=\u001b[39mdevice)\n\u001b[0;32m      3\u001b[0m base_speaker_tts\u001b[38;5;241m.\u001b[39mload_ckpt(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mckpt_base\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/checkpoint.pth\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m      5\u001b[0m source_se \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mload(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mckpt_base\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/zh_default_se.pth\u001b[39m\u001b[38;5;124m'\u001b[39m)\u001b[38;5;241m.\u001b[39mto(device)\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'BaseSpeakerTTS' is not defined"
+     ]
+    }
+   ],
    "source": [
     "\n",
     "ckpt_base = 'checkpoints/base_speakers/ZH'\n",
@@ -207,6 +291,14 @@
    "source": [
     "**Tech for good.** For people who will deploy OpenVoice for public usage: We offer you the option to add watermark to avoid potential misuse. Please see the ToneColorConverter class. **MyShell reserves the ability to detect whether an audio is generated by OpenVoice**, no matter whether the watermark is added or not."
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1cb144de-9bff-4024-a474-a49dd5d6b2e4",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -228,7 +320,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,

env/Lib/site-packages/Cython-3.0.10.dist-info/COPYING.txt

@@ -0,0 +1,19 @@
+The original Pyrex code as of 2006-04 is licensed under the following
+license: "Copyright stuff: Pyrex is free of restrictions. You may use,
+redistribute, modify and distribute modified versions."
+
+------------------
+
+Cython, which derives from Pyrex, is licensed under the Apache 2.0
+Software License.  More precisely, all modifications and new code
+made to go from Pyrex to Cython are so licensed.
+
+See LICENSE.txt for more details.
+
+------------------
+
+The output of a Cython compilation is NOT considered a derivative
+work of Cython.  Specifically, though the compilation process may
+embed snippets of varying lengths into the final output, these
+snippets, as embedded in the output, do not encumber the resulting
+output with any license restrictions.

env/Lib/site-packages/Cython-3.0.10.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip