优化笔记本、翻译并重新引入自动push (#48)

* optimize: 精简未用到的配置项并在特征提取初步引入mps * add cmd argument: --noautoopen * fix: i18n * fix * fix * add genlocale workflow * add unitest * fix * fix * fix * 优化笔记本 * reintroduce Push changes * disable genlocale on non-main branch * 将笔记本checkout改为stable
2026-01-19 10:31:41 +00:00 · 2023-04-13 21:32:08 +08:00
parent 55135e0a0e
commit 99996fbe8a
6 changed files with 90 additions and 25 deletions
--- a/Retrieval_based_Voice_Conversion_WebUI.ipynb
+++ b/Retrieval_based_Voice_Conversion_WebUI.ipynb
@@ -58,7 +58,7 @@
      "source": [
        "#@title 克隆仓库\n",
        "\n",
-        "!git clone --depth=1 https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI\n",
+        "!git clone --depth=1 -b stable https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI\n",
        "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
        "!mkdir -p pretrained uvr5_weights"
      ],
@@ -80,11 +80,22 @@
      "execution_count": null,
      "outputs": []
    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#@title 安装aria2\n",
+        "!apt -y install -qq aria2"
+      ],
+      "metadata": {
+        "id": "pqE0PrnuRqI2"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
    {
      "cell_type": "code",
      "source": [
        "#@title 下载底模\n",
-        "!apt -y install -qq aria2\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
@@ -96,12 +107,7 @@
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
-        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth\n",
-        "\n",
-        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
-        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth\n",
-        "\n",
-        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
+        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth"
      ],
      "metadata": {
        "id": "UG3XpUwEomUz"
@@ -109,6 +115,31 @@
      "execution_count": null,
      "outputs": []
    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#@title 下载人声分离模型\n",
+        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
+        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
+      ],
+      "metadata": {
+        "id": "HugjmZqZRuiF"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#@title 下载hubert_base\n",
+        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
+      ],
+      "metadata": {
+        "id": "2RCaT9FTR0ej"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
    {
      "cell_type": "code",
      "source": [
@@ -223,8 +254,12 @@
        "#@title 手动预处理（不推荐）\n",
        "#@markdown 模型名\n",
        "MODELNAME = \"lulu\"  #@param {type:\"string\"}\n",
+        "#@markdown 采样率\n",
+        "BITRATE = 48000  #@param {type:\"integer\"}\n",
+        "#@markdown 使用的进程数\n",
+        "THREADCOUNT = 8  #@param {type:\"integer\"}\n",
        "\n",
-        "!python3 trainset_preprocess_pipeline_print.py /content/dataset 48000 8 logs/{MODELNAME} True\n"
+        "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True\n"
      ],
      "metadata": {
        "id": "ZKAyuKb9J6dz"
@@ -238,8 +273,14 @@
        "#@title 手动提取特征（不推荐）\n",
        "#@markdown 模型名\n",
        "MODELNAME = \"lulu\"  #@param {type:\"string\"}\n",
+        "#@markdown 使用的进程数\n",
+        "THREADCOUNT = 8  #@param {type:\"integer\"}\n",
+        "#@markdown 音高提取算法\n",
+        "ALGO = \"harvest\"  #@param {type:\"string\"}\n",
        "\n",
-        "!python3 extract_feature_print.py 1 0 0 logs/{MODELNAME}\n"
+        "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
+        "\n",
+        "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME}\n"
      ],
      "metadata": {
        "id": "CrxJqzAUKmPJ"
@@ -253,14 +294,22 @@
        "#@title 手动训练（不推荐）\n",
        "#@markdown 模型名\n",
        "MODELNAME = \"lulu\"  #@param {type:\"string\"}\n",
+        "#@markdown 使用的GPU\n",
+        "USEGPU = \"0\"  #@param {type:\"string\"}\n",
+        "#@markdown 批大小\n",
+        "BATCHSIZE = 32  #@param {type:\"integer\"}\n",
        "#@markdown 停止的epoch\n",
        "MODELEPOCH = 3200  #@param {type:\"integer\"}\n",
        "#@markdown 保存epoch间隔\n",
        "EPOCHSAVE = 100  #@param {type:\"integer\"}\n",
        "#@markdown 采样率\n",
        "MODELSAMPLE = \"48k\"  #@param {type:\"string\"}\n",
+        "#@markdown 是否缓存训练集\n",
+        "CACHEDATA = 1  #@param {type:\"integer\"}\n",
+        "#@markdown 是否仅保存最新的ckpt文件\n",
+        "ONLYLATEST = 0  #@param {type:\"integer\"}\n",
        "\n",
-        "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs 32 -g 0 -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l 0 -c 1\n"
+        "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}\n"
      ],
      "metadata": {
        "id": "IMLPLKOaKj58"