feat: 初识提交

.gitignore

+.idea
+chenyh

hf_down.py

+# pip install huggingface-cli
+import os
+import requests
+import json
+
+os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
+
+model_list = [
+        "coqui/XTTS-v2"
+]
+
+for model_path in model_list:
+    os.system(f"huggingface-cli download --resume-download  {model_path} --local-dir ./{model_path} --local-dir-use-symlinks False")
\ No newline at end of file

start.sh

+#!/bin/bash
+
+cd /root/voice-clone
+python app.py

voice-clone/README.md

+---
+title: Voice Clone
+emoji: 🗣️
+colorFrom: pink
+colorTo: indigo
+sdk: gradio
+sdk_version: 4.26.0
+app_file: app.py
+pinned: false
+disable_embedding: true
+models:
+  - coqui/XTTS-v2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

voice-clone/app.py

+import spaces
+import gradio as gr
+import torch
+from TTS.api import TTS
+import os
+
+os.environ["COQUI_TOS_AGREED"] = "1"
+
+device = "cuda"
+
+tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)
+
+
+@spaces.GPU(enable_queue=True)
+def clone(text, audio, language):
+    tts.tts_to_file(text=text, speaker_wav=audio, language=language, file_path="./output.wav")
+    return "./output.wav"
+
+
+iface = gr.Interface(fn=clone,
+                     inputs=[gr.Textbox(label='Text'),
+                             gr.Audio(type='filepath', label='Voice reference audio file'),
+                             gr.Dropdown(label='Language',
+                                         choices=['en - English', 'fr - French', 'ar - Arabic', 'es - Spanish',
+                                                  'zh - Chinese', 'ru - Russian', 'pt - Portuguese', 'it - Italian',
+                                                  'de - German', 'nl - Dutch'])],
+                     outputs=gr.Audio(type='filepath'),
+                     title='Voice Clone',
+                     description="""
+                     by [Tony Assi](https://www.tonyassi.com/)
+                     This space uses xtts_v2 model. Non-commercial use only. [Coqui Public Model License](https://coqui.ai/cpml)
+
+                     Please ❤️ this Space. <a href="mailto: tony.assi.media@gmail.com">Email me</a>.
+                     """,
+                     theme=gr.themes.Base(primary_hue="teal", secondary_hue="teal", neutral_hue="slate"),
+                     examples=[["Hey! It's me Dorthy, from the Wizard of Oz. Type in whatever you'd like me to say.",
+                                "./audio/Wizard-of-Oz-Dorthy.wav", "en - English"],
+                               ["It's me Vito Corleone, from the Godfather. Type in whatever you'd like me to say.",
+                                "./audio/Godfather.wav", "en - English"],
+                               ["Hey, it's me Paris Hilton. Type in whatever you'd like me to say.",
+                                "./audio/Paris-Hilton.mp3", "en - English"],
+                               ["Hey, it's me Megan Fox from Transformers. Type in whatever you'd like me to say.",
+                                "./audio/Megan-Fox.mp3", "en - English"],
+                               ["Hey there, it's me Jeff Goldblum. Type in whatever you'd like me to say.",
+                                "./audio/Jeff-Goldblum.mp3", "en - English"], ])
+iface.launch()
\ No newline at end of file

voice-clone/requirements.txt

+TTS
+torch
\ No newline at end of file

启动器.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e5c5a211-2ccd-4341-af10-ac546484b91f",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## 说明\n",
+    "- 启动需要加载模型，需要1分钟左右的时间\n",
+    "- 启动和重启 Notebook 点上方工具栏中的「重启并运行所有单元格」。出现如下内容就算成功了：\n",
+    "    - `Running on local URL:  http://0.0.0.0:7860`\n",
+    "    - `Running on public URL: https://xxxxxxxxxxxxxxx.gradio.live`\n",
+    "- 通过以下方式开启页面：\n",
+    "    - 控制台打开「自定义服务」了，访问自定义服务端口号设置为7860\n",
+    "    - 直接打开显示的公开链接`public URL`\n",
+    "\n",
+    "## 功能介绍\n",
+    "- 原项目地址：https://huggingface.co/spaces/tonyassi/voice-clone/tree/main\n",
+    "- voice-clone：一款声音克隆工具，无需训练，仅需上传一段参考人声、文字即可生成语音。"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "53a96614-e2d2-4710-a82b-0d5ca9cb9872",
+   "metadata": {
+    "tags": [],
+    "is_executing": true
+   },
+   "outputs": [],
+   "source": [
+    "# 启动\n",
+    "!sh start.sh"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9e81ae9d-3a34-43a0-943a-ff5e9d6ce961",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}