From 3c1269e520d0720b65dc5b285ba469ef0b7e5ae7 Mon Sep 17 00:00:00 2001
From: litagin02 <litagin02@gmail.com>
Date: Wed, 13 Mar 2024 15:41:46 +0900
Subject: [PATCH] Add library usage example notebook

---
 library.ipynb | 117 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 117 insertions(+)
 create mode 100644 library.ipynb

diff --git a/library.ipynb b/library.ipynb
new file mode 100644
index 0000000..81a1028
--- /dev/null
+++ b/library.ipynb
@@ -0,0 +1,117 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Style-Bert-VITS2ライブラリの使用例\n",
+        "\n",
+        "`pip install style-bert-vits2`を使った、colabで動く使用例です。"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "LLrngKcQEAyP"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install style-bert-vits2==2.4.dev0"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9xRtfUg5EZkx"
+      },
+      "outputs": [],
+      "source": [
+        "from style_bert_vits2.nlp import bert_models\n",
+        "from style_bert_vits2.constants import Languages\n",
+        "\n",
+        "\n",
+        "bert_models.load_model(Languages.JP, \"ku-nlp/deberta-v2-large-japanese-char-wwm\")\n",
+        "bert_models.load_tokenizer(Languages.JP, \"ku-nlp/deberta-v2-large-japanese-char-wwm\")\n",
+        "# bert_models.load_model(Languages.EN, \"microsoft/deberta-v3-large\")\n",
+        "# bert_models.load_tokenizer(Languages.EN, \"microsoft/deberta-v3-large\")\n",
+        "# bert_models.load_model(Languages.ZH, \"hfl/chinese-roberta-wwm-ext-large\")\n",
+        "# bert_models.load_tokenizer(Languages.ZH, \"hfl/chinese-roberta-wwm-ext-large\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "q2V9d3HyFAr_"
+      },
+      "outputs": [],
+      "source": [
+        "from pathlib import Path\n",
+        "from huggingface_hub import hf_hub_download\n",
+        "\n",
+        "\n",
+        "model_file = \"jvnv-F1-jp/jvnv-F1-jp_e160_s14000.safetensors\"\n",
+        "config_file = \"jvnv-F1-jp/config.json\"\n",
+        "style_file = \"jvnv-F1-jp/style_vectors.npy\"\n",
+        "\n",
+        "for file in [model_file, config_file, style_file]:\n",
+        "    print(file)\n",
+        "    hf_hub_download(\n",
+        "        \"litagin/style_bert_vits2_jvnv\",\n",
+        "        file,\n",
+        "        local_dir=\"model_assets\"\n",
+        "    )"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "hJa31MEUFhe4"
+      },
+      "outputs": [],
+      "source": [
+        "from style_bert_vits2.tts_model import TTSModel\n",
+        "\n",
+        "assets_root = Path(\"model_assets\")\n",
+        "\n",
+        "model = TTSModel(\n",
+        "    model_path=assets_root / model_file,\n",
+        "    config_path = assets_root / config_file,\n",
+        "    style_vec_path = assets_root / style_file,\n",
+        "    device=\"cpu\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Gal0tqrtGXZx"
+      },
+      "outputs": [],
+      "source": [
+        "from IPython.display import Audio, display\n",
+        "\n",
+        "sr, audio = model.infer(text=\"こんにちは\")\n",
+        "display(Audio(audio, rate=sr))"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}