mirror of
https://github.com/harry0703/MoneyPrinterTurbo.git
synced 2026-02-21 16:37:21 +08:00
Merge branch 'harry0703:main' into main
This commit is contained in:
cpanel10x
GitHub
commit
7e8c901fd4
@ -21,3 +21,4 @@ __pycache__/
|
||||
.svn/
|
||||
|
||||
storage/
|
||||
config.toml
|
||||
|
||||
4
.gitignore
vendored
4
.gitignore
vendored
@ -9,4 +9,6 @@
|
||||
/app/utils/__pycache__/
|
||||
/*/__pycache__/*
|
||||
.vscode
|
||||
/**/.streamlit
|
||||
/**/.streamlit
|
||||
__pycache__
|
||||
logs/
|
||||
21
Dockerfile
21
Dockerfile
@ -4,7 +4,7 @@ FROM python:3.10-slim
|
||||
# Set the working directory in the container
|
||||
WORKDIR /MoneyPrinterTurbo
|
||||
|
||||
ENV PYTHONPATH="/MoneyPrinterTurbo:$PYTHONPATH"
|
||||
ENV PYTHONPATH="/MoneyPrinterTurbo"
|
||||
|
||||
# Install system dependencies
|
||||
RUN apt-get update && apt-get install -y \
|
||||
@ -17,11 +17,7 @@ RUN apt-get update && apt-get install -y \
|
||||
RUN sed -i '/<policy domain="path" rights="none" pattern="@\*"/d' /etc/ImageMagick-6/policy.xml
|
||||
|
||||
# Copy the current directory contents into the container at /MoneyPrinterTurbo
|
||||
COPY ./app ./app
|
||||
COPY ./webui ./webui
|
||||
COPY ./resource ./resource
|
||||
COPY ./requirements.txt ./requirements.txt
|
||||
COPY ./main.py ./main.py
|
||||
COPY . .
|
||||
|
||||
# Install Python dependencies
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
@ -30,8 +26,13 @@ RUN pip install --no-cache-dir -r requirements.txt
|
||||
EXPOSE 8501
|
||||
|
||||
# Command to run the application
|
||||
CMD ["streamlit", "run", "./webui/Main.py","--browser.serverAddress=0.0.0.0","--server.enableCORS=True","--browser.gatherUsageStats=False"]
|
||||
CMD ["streamlit", "run", "./webui/Main.py","--browser.serverAddress=127.0.0.1","--server.enableCORS=True","--browser.gatherUsageStats=False"]
|
||||
|
||||
# At runtime, mount the config.toml file from the host into the container
|
||||
# using Docker volumes. Example usage:
|
||||
# docker run -v ./config.toml:/MoneyPrinterTurbo/config.toml -v ./storage:/MoneyPrinterTurbo/storage -p 8501:8501 moneyprinterturbo
|
||||
# 1. Build the Docker image using the following command
|
||||
# docker build -t moneyprinterturbo .
|
||||
|
||||
# 2. Run the Docker container using the following command
|
||||
## For Linux or MacOS:
|
||||
# docker run -v $(pwd)/config.toml:/MoneyPrinterTurbo/config.toml -v $(pwd)/storage:/MoneyPrinterTurbo/storage -p 8501:8501 moneyprinterturbo
|
||||
## For Windows:
|
||||
# docker run -v %cd%/config.toml:/MoneyPrinterTurbo/config.toml -v %cd%/storage:/MoneyPrinterTurbo/storage -p 8501:8501 moneyprinterturbo
|
||||
15
README-en.md
15
README-en.md
@ -10,9 +10,9 @@
|
||||
|
||||
<h3>English | <a href="README.md">简体中文</a></h3>
|
||||
|
||||
|
||||
> Thanks to [RootFTW](https://github.com/Root-FTW) for the translation
|
||||
|
||||
<div align="center">
|
||||
<a href="https://trendshift.io/repositories/8731" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8731" alt="harry0703%2FMoneyPrinterTurbo | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
|
||||
</div>
|
||||
|
||||
Simply provide a <b>topic</b> or <b>keyword</b> for a video, and it will automatically generate the video copy, video
|
||||
materials, video subtitles, and video background music before synthesizing a high-definition short video.
|
||||
@ -59,8 +59,7 @@ https://reccloud.com
|
||||
- [x] Supports integration with various models such as **OpenAI**, **moonshot**, **Azure**, **gpt4free**, **one-api**,
|
||||
**qianwen**, **Google Gemini**, **Ollama** and more
|
||||
|
||||
❓[How to Use the Free OpenAI GPT-3.5 Model?](https://github.com/harry0703/MoneyPrinterTurbo/blob/main/README-en.md#common-questions-)
|
||||
|
||||
❓[How to Use the Free OpenAI GPT-3.5 Model?](https://github.com/harry0703/MoneyPrinterTurbo/blob/main/README-en.md#common-questions-)
|
||||
|
||||
### Future Plans 📅
|
||||
|
||||
@ -261,12 +260,16 @@ own fonts.
|
||||
## Common Questions 🤔
|
||||
|
||||
### ❓How to Use the Free OpenAI GPT-3.5 Model?
|
||||
[OpenAI has announced that ChatGPT with 3.5 is now free](https://openai.com/blog/start-using-chatgpt-instantly), and developers have wrapped it into an API for direct usage.
|
||||
|
||||
[OpenAI has announced that ChatGPT with 3.5 is now free](https://openai.com/blog/start-using-chatgpt-instantly), and
|
||||
developers have wrapped it into an API for direct usage.
|
||||
|
||||
**Ensure you have Docker installed and running**. Execute the following command to start the Docker service:
|
||||
|
||||
```shell
|
||||
docker run -p 3040:3040 missuo/freegpt35
|
||||
```
|
||||
|
||||
Once successfully started, modify the `config.toml` configuration as follows:
|
||||
|
||||
- Set `llm_provider` to `openai`
|
||||
|
||||
98
README.md
98
README.md
@ -9,6 +9,9 @@
|
||||
</p>
|
||||
<br>
|
||||
<h3>简体中文 | <a href="README-en.md">English</a></h3>
|
||||
<div align="center">
|
||||
<a href="https://trendshift.io/repositories/8731" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8731" alt="harry0703%2FMoneyPrinterTurbo | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
|
||||
</div>
|
||||
<br>
|
||||
只需提供一个视频 <b>主题</b> 或 <b>关键词</b> ，就可以全自动生成视频文案、视频素材、视频字幕、视频背景音乐，然后合成一个高清的短视频。
|
||||
<br>
|
||||
@ -26,7 +29,6 @@
|
||||
## 特别感谢 🙏
|
||||
|
||||
由于该项目的 **部署** 和 **使用**，对于一些小白用户来说，还是 **有一定的门槛**，在此特别感谢
|
||||
|
||||
**录咖（AI智能 多媒体服务平台）** 网站基于该项目，提供的免费`AI视频生成器`服务，可以不用部署，直接在线使用，非常方便。
|
||||
|
||||
- 中文版：https://reccloud.cn
|
||||
@ -34,6 +36,14 @@
|
||||
|
||||
|
||||
|
||||
## 感谢赞助 🙏
|
||||
|
||||
感谢佐糖 https://picwish.cn 对该项目的支持和赞助，使得该项目能够持续的更新和维护。
|
||||
|
||||
佐糖专注于**图像处理领域**，提供丰富的**图像处理工具**，将复杂操作极致简化，真正实现让图像处理更简单。
|
||||
|
||||
|
||||
|
||||
## 功能特性 🎯
|
||||
|
||||
- [x] 完整的 **MVC架构**，代码 **结构清晰**，易于维护，支持 `API` 和 `Web界面`
|
||||
@ -50,7 +60,8 @@
|
||||
- [x] 视频素材来源 **高清**，而且 **无版权**
|
||||
- [x] 支持 **OpenAI**、**moonshot**、**Azure**、**gpt4free**、**one-api**、**通义千问**、**Google Gemini**、**Ollama** 等多种模型接入
|
||||
|
||||
❓[如何使用免费的 **OpenAI GPT-3.5** 模型?](https://github.com/harry0703/MoneyPrinterTurbo?tab=readme-ov-file#%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98-)
|
||||
❓[如何使用免费的 **OpenAI GPT-3.5
|
||||
** 模型?](https://github.com/harry0703/MoneyPrinterTurbo?tab=readme-ov-file#%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98-)
|
||||
|
||||
### 后期计划 📅
|
||||
|
||||
@ -59,13 +70,26 @@
|
||||
- [ ] 增加视频转场效果，使其看起来更加的流畅
|
||||
- [ ] 增加更多视频素材来源，优化视频素材和文案的匹配度
|
||||
- [ ] 增加视频长度选项：短、中、长
|
||||
- [ ] 打包成一键启动包（Windows，macOS），方便使用
|
||||
- [ ] 增加免费网络代理，让访问OpenAI和素材下载不再受限
|
||||
- [ ] 可以使用自己的素材
|
||||
- [ ] 朗读声音和背景音乐，提供实时试听
|
||||
- [ ] 支持更多的语音合成服务商，比如 OpenAI TTS, Azure TTS
|
||||
- [ ] 支持更多的语音合成服务商，比如 OpenAI TTS
|
||||
- [ ] 自动上传到YouTube平台
|
||||
|
||||
## 交流讨论 💬
|
||||
|
||||
<img src="docs/wechat-03.jpg" width="150">
|
||||
|
||||
## 更新日志
|
||||
|
||||
### 2024-04-16 v1.1.2
|
||||
|
||||
- 支持azure新发布的9种语音合成声音（需要配置API
|
||||
KEY） [9个更真实的AI对话声音](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/9-more-realistic-ai-voices-for-conversations-now-generally/ba-p/4099471)
|
||||
- 优化字幕显示
|
||||
- 修复内存泄露问题
|
||||
- 一些其他的bug修复和优化
|
||||
|
||||
## 视频演示 📺
|
||||
|
||||
### 竖屏 9:16
|
||||
@ -74,12 +98,14 @@
|
||||
<thead>
|
||||
<tr>
|
||||
<th align="center"><g-emoji class="g-emoji" alias="arrow_forward">▶️</g-emoji> 《如何增加生活的乐趣》</th>
|
||||
<th align="center"><g-emoji class="g-emoji" alias="arrow_forward">▶️</g-emoji> 《金钱的作用》<br>更真实的合成声音</th>
|
||||
<th align="center"><g-emoji class="g-emoji" alias="arrow_forward">▶️</g-emoji> 《生命的意义是什么》</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td align="center"><video src="https://github.com/harry0703/MoneyPrinterTurbo/assets/4928832/a84d33d5-27a2-4aba-8fd0-9fb2bd91c6a6"></video></td>
|
||||
<td align="center"><video src="https://github.com/harry0703/MoneyPrinterTurbo/assets/4928832/af2f3b0b-002e-49fe-b161-18ba91c055e8"></video></td>
|
||||
<td align="center"><video src="https://github.com/harry0703/MoneyPrinterTurbo/assets/4928832/112c9564-d52b-4472-99ad-970b75f66476"></video></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
@ -102,8 +128,28 @@
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
## 配置要求 📦
|
||||
|
||||
- 建议最低 CPU 4核或以上，内存 8G 或以上，显卡非必须
|
||||
- Windows 10 或 MacOS 11.0 以上系统
|
||||
|
||||
## 快速开始 🚀
|
||||
|
||||
下载一键启动包，解压直接使用
|
||||
|
||||
### Windows
|
||||
|
||||
- 百度网盘: https://pan.baidu.com/s/1bpGjgQVE5sADZRn3A6F87w?pwd=xt16 提取码: xt16
|
||||
|
||||
下载后，建议先**双击执行** `update.bat` 更新到**最新代码**，然后双击 `start.bat` 启动Web界面
|
||||
|
||||
### 其他系统
|
||||
还没有制作一键启动包，看下面的 **安装部署** 部分，建议使用 **docker** 部署，更加方便。
|
||||
|
||||
## 安装部署 📥
|
||||
|
||||
### 前提条件
|
||||
|
||||
- 尽量不要使用 **中文路径**，避免出现一些无法预料的问题
|
||||
- 请确保你的 **网络** 是正常的，VPN需要打开`全局流量`模式
|
||||
|
||||
@ -134,6 +180,7 @@ git clone https://github.com/harry0703/MoneyPrinterTurbo.git
|
||||
如果未安装 Docker，请先安装 https://www.docker.com/products/docker-desktop/
|
||||
|
||||
如果是Windows系统，请参考微软的文档：
|
||||
|
||||
1. https://learn.microsoft.com/zh-cn/windows/wsl/install
|
||||
2. https://learn.microsoft.com/zh-cn/windows/wsl/tutorials/wsl-containers
|
||||
|
||||
@ -212,6 +259,7 @@ webui.bat
|
||||
conda activate MoneyPrinterTurbo
|
||||
sh webui.sh
|
||||
```
|
||||
|
||||
启动后，会自动打开浏览器
|
||||
|
||||
#### ④ 启动API服务 🚀
|
||||
@ -226,21 +274,45 @@ python main.py
|
||||
|
||||
所有支持的声音列表，可以查看：[声音列表](./docs/voice-list.txt)
|
||||
|
||||
2024-04-16 v1.1.2 新增了9种Azure的语音合成声音，需要配置API KEY，该声音合成的更加真实。
|
||||
|
||||
## 字幕生成 📜
|
||||
|
||||
当前支持2种字幕生成方式：
|
||||
|
||||
- edge: 生成速度更快，性能更好，对电脑配置没有要求，但是质量可能不稳定
|
||||
- whisper: 生成速度较慢，性能较差，对电脑配置有一定要求，但是质量更可靠。
|
||||
- **edge**: 生成`速度快`，性能更好，对电脑配置没有要求，但是质量可能不稳定
|
||||
- **whisper**: 生成`速度慢`，性能较差，对电脑配置有一定要求，但是`质量更可靠`。
|
||||
|
||||
可以修改 `config.toml` 配置文件中的 `subtitle_provider` 进行切换
|
||||
|
||||
建议使用 `edge` 模式，如果生成的字幕质量不好，再切换到 `whisper` 模式
|
||||
|
||||
> 注意：
|
||||
|
||||
1. whisper 模式下需要到 HuggingFace 下载一个模型文件，大约 3GB 左右，请确保网络通畅
|
||||
2. 如果留空，表示不生成字幕。
|
||||
|
||||
> 由于国内无法访问 HuggingFace，可以使用以下方法下载 `whisper-large-v3` 的模型文件
|
||||
|
||||
下载地址：
|
||||
|
||||
- 百度网盘: https://pan.baidu.com/s/11h3Q6tsDtjQKTjUu3sc5cA?pwd=xjs9
|
||||
- 夸克网盘：https://pan.quark.cn/s/3ee3d991d64b
|
||||
|
||||
模型下载后解压，整个目录放到 `.\MoneyPrinterTurbo\models` 里面，
|
||||
最终的文件路径应该是这样: `.\MoneyPrinterTurbo\models\whisper-large-v3`
|
||||
|
||||
```
|
||||
MoneyPrinterTurbo
|
||||
├─models
|
||||
│ └─whisper-large-v3
|
||||
│ config.json
|
||||
│ model.bin
|
||||
│ preprocessor_config.json
|
||||
│ tokenizer.json
|
||||
│ vocabulary.json
|
||||
```
|
||||
|
||||
## 背景音乐 🎵
|
||||
|
||||
用于视频的背景音乐，位于项目的 `resource/songs` 目录下。
|
||||
@ -253,19 +325,22 @@ python main.py
|
||||
## 常见问题 🤔
|
||||
|
||||
### ❓如何使用免费的OpenAI GPT-3.5模型?
|
||||
|
||||
[OpenAI宣布ChatGPT里面3.5已经免费了](https://openai.com/blog/start-using-chatgpt-instantly)，有开发者将其封装成了API，可以直接调用
|
||||
|
||||
**确保你安装和启动了docker服务**，执行以下命令启动docker服务
|
||||
|
||||
```shell
|
||||
docker run -p 3040:3040 missuo/freegpt35
|
||||
```
|
||||
|
||||
启动成功后，修改 `config.toml` 中的配置
|
||||
|
||||
- `llm_provider` 设置为 `openai`
|
||||
- `openai_api_key` 随便填写一个即可，比如 '123456'
|
||||
- `openai_base_url` 改为 `http://localhost:3040/v1/`
|
||||
- `openai_model_name` 改为 `gpt-3.5-turbo`
|
||||
|
||||
|
||||
### ❓AttributeError: 'str' object has no attribute 'choices'`
|
||||
|
||||
这个问题是由于 OpenAI 或者其他 LLM，没有返回正确的回复导致的。
|
||||
@ -375,14 +450,6 @@ pip install Pillow==8.4.0
|
||||
|
||||
- 可以提交 [issue](https://github.com/harry0703/MoneyPrinterTurbo/issues)
|
||||
或者 [pull request](https://github.com/harry0703/MoneyPrinterTurbo/pulls)。
|
||||
- 也可以关注我的 **抖音** 或 **视频号**：`网旭哈瑞.AI`
|
||||
- 我会在上面发布一些 **使用教程** 和 **纯技术** 分享。
|
||||
- 如果有更新和优化，我也会在上面 **及时通知**。
|
||||
- 有问题也可以在上面 **留言**，我会 **尽快回复**。
|
||||
|
||||
| 抖音 | | 视频号 |
|
||||
|:---------------------------------------:|:------------:|:-------------------------------------------:|
|
||||
| <img src="docs/douyin.jpg" width="180"> | | <img src="docs/shipinghao.jpg" width="200"> |
|
||||
|
||||
## 参考项目 📚
|
||||
|
||||
@ -393,7 +460,6 @@ pip install Pillow==8.4.0
|
||||
|
||||
点击查看 [`LICENSE`](LICENSE) 文件
|
||||
|
||||
|
||||
## Star History
|
||||
|
||||
[](https://star-history.com/#harry0703/MoneyPrinterTurbo&Date)
|
||||
@ -1,31 +1,51 @@
|
||||
import os
|
||||
import socket
|
||||
import toml
|
||||
import shutil
|
||||
from loguru import logger
|
||||
|
||||
root_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.realpath(__file__))))
|
||||
config_file = f"{root_dir}/config.toml"
|
||||
if not os.path.isfile(config_file):
|
||||
example_file = f"{root_dir}/config.example.toml"
|
||||
if os.path.isfile(example_file):
|
||||
import shutil
|
||||
|
||||
shutil.copyfile(example_file, config_file)
|
||||
logger.info(f"copy config.example.toml to config.toml")
|
||||
|
||||
logger.info(f"load config from file: {config_file}")
|
||||
def load_config():
|
||||
# fix: IsADirectoryError: [Errno 21] Is a directory: '/MoneyPrinterTurbo/config.toml'
|
||||
if os.path.isdir(config_file):
|
||||
shutil.rmtree(config_file)
|
||||
|
||||
try:
|
||||
_cfg = toml.load(config_file)
|
||||
except Exception as e:
|
||||
logger.warning(f"load config failed: {str(e)}, try to load as utf-8-sig")
|
||||
with open(config_file, mode="r", encoding='utf-8-sig') as fp:
|
||||
_cfg_content = fp.read()
|
||||
_cfg = toml.loads(_cfg_content)
|
||||
if not os.path.isfile(config_file):
|
||||
example_file = f"{root_dir}/config.example.toml"
|
||||
if os.path.isfile(example_file):
|
||||
shutil.copyfile(example_file, config_file)
|
||||
logger.info(f"copy config.example.toml to config.toml")
|
||||
|
||||
logger.info(f"load config from file: {config_file}")
|
||||
|
||||
try:
|
||||
_config_ = toml.load(config_file)
|
||||
except Exception as e:
|
||||
logger.warning(f"load config failed: {str(e)}, try to load as utf-8-sig")
|
||||
with open(config_file, mode="r", encoding='utf-8-sig') as fp:
|
||||
_cfg_content = fp.read()
|
||||
_config_ = toml.loads(_cfg_content)
|
||||
return _config_
|
||||
|
||||
|
||||
def save_config():
|
||||
with open(config_file, "w", encoding="utf-8") as f:
|
||||
_cfg["app"] = app
|
||||
_cfg["whisper"] = whisper
|
||||
_cfg["pexels"] = pexels
|
||||
_cfg["azure"] = azure
|
||||
_cfg["ui"] = ui
|
||||
f.write(toml.dumps(_cfg))
|
||||
|
||||
|
||||
_cfg = load_config()
|
||||
app = _cfg.get("app", {})
|
||||
whisper = _cfg.get("whisper", {})
|
||||
pexels = _cfg.get("pexels", {})
|
||||
azure = _cfg.get("azure", {})
|
||||
ui = _cfg.get("ui", {})
|
||||
|
||||
hostname = socket.gethostname()
|
||||
@ -36,7 +56,7 @@ listen_port = _cfg.get("listen_port", 8080)
|
||||
project_name = _cfg.get("project_name", "MoneyPrinterTurbo")
|
||||
project_description = _cfg.get("project_description",
|
||||
"<a href='https://github.com/harry0703/MoneyPrinterTurbo'>https://github.com/harry0703/MoneyPrinterTurbo</a>")
|
||||
project_version = _cfg.get("project_version", "1.0.1")
|
||||
project_version = _cfg.get("project_version", "1.1.2")
|
||||
reload_debug = False
|
||||
|
||||
imagemagick_path = app.get("imagemagick_path", "")
|
||||
@ -47,18 +67,4 @@ ffmpeg_path = app.get("ffmpeg_path", "")
|
||||
if ffmpeg_path and os.path.isfile(ffmpeg_path):
|
||||
os.environ["IMAGEIO_FFMPEG_EXE"] = ffmpeg_path
|
||||
|
||||
|
||||
# __cfg = {
|
||||
# "hostname": hostname,
|
||||
# "listen_host": listen_host,
|
||||
# "listen_port": listen_port,
|
||||
# }
|
||||
# logger.info(__cfg)
|
||||
|
||||
|
||||
def save_config():
|
||||
with open(config_file, "w", encoding="utf-8") as f:
|
||||
_cfg["app"] = app
|
||||
_cfg["whisper"] = whisper
|
||||
_cfg["pexels"] = pexels
|
||||
f.write(toml.dumps(_cfg))
|
||||
logger.info(f"{project_name} v{project_version}")
|
||||
|
||||
@ -1,8 +1,10 @@
|
||||
import os
|
||||
import glob
|
||||
import pathlib
|
||||
import shutil
|
||||
|
||||
from fastapi import Request, Depends, Path, BackgroundTasks, UploadFile
|
||||
from fastapi.responses import FileResponse, StreamingResponse
|
||||
from fastapi.params import File
|
||||
from loguru import logger
|
||||
|
||||
@ -78,7 +80,7 @@ def get_task(request: Request, task_id: str = Path(..., description="Task ID"),
|
||||
|
||||
|
||||
@router.delete("/tasks/{task_id}", response_model=TaskDeletionResponse, summary="Delete a generated short video task")
|
||||
def create_video(request: Request, task_id: str = Path(..., description="Task ID")):
|
||||
def delete_video(request: Request, task_id: str = Path(..., description="Task ID")):
|
||||
request_id = base.get_task_id(request)
|
||||
task = sm.state.get_task(task_id)
|
||||
if task:
|
||||
@ -89,7 +91,7 @@ def create_video(request: Request, task_id: str = Path(..., description="Task ID
|
||||
|
||||
sm.state.delete_task(task_id)
|
||||
logger.success(f"video deleted: {utils.to_json(task)}")
|
||||
return utils.get_response(200, task)
|
||||
return utils.get_response(200)
|
||||
|
||||
raise HttpException(task_id=task_id, status_code=404, message=f"{request_id}: task not found")
|
||||
|
||||
@ -130,3 +132,63 @@ def upload_bgm_file(request: Request, file: UploadFile = File(...)):
|
||||
return utils.get_response(200, response)
|
||||
|
||||
raise HttpException('', status_code=400, message=f"{request_id}: Only *.mp3 files can be uploaded")
|
||||
|
||||
|
||||
@router.get("/stream/{file_path:path}")
|
||||
async def stream_video(request: Request, file_path: str):
|
||||
tasks_dir = utils.task_dir()
|
||||
video_path = os.path.join(tasks_dir, file_path)
|
||||
range_header = request.headers.get('Range')
|
||||
video_size = os.path.getsize(video_path)
|
||||
start, end = 0, video_size - 1
|
||||
|
||||
length = video_size
|
||||
if range_header:
|
||||
range_ = range_header.split('bytes=')[1]
|
||||
start, end = [int(part) if part else None for part in range_.split('-')]
|
||||
if start is None:
|
||||
start = video_size - end
|
||||
end = video_size - 1
|
||||
if end is None:
|
||||
end = video_size - 1
|
||||
length = end - start + 1
|
||||
|
||||
def file_iterator(file_path, offset=0, bytes_to_read=None):
|
||||
with open(file_path, 'rb') as f:
|
||||
f.seek(offset, os.SEEK_SET)
|
||||
remaining = bytes_to_read or video_size
|
||||
while remaining > 0:
|
||||
bytes_to_read = min(4096, remaining)
|
||||
data = f.read(bytes_to_read)
|
||||
if not data:
|
||||
break
|
||||
remaining -= len(data)
|
||||
yield data
|
||||
|
||||
response = StreamingResponse(file_iterator(video_path, start, length), media_type='video/mp4')
|
||||
response.headers['Content-Range'] = f'bytes {start}-{end}/{video_size}'
|
||||
response.headers['Accept-Ranges'] = 'bytes'
|
||||
response.headers['Content-Length'] = str(length)
|
||||
response.status_code = 206 # Partial Content
|
||||
|
||||
return response
|
||||
|
||||
|
||||
@router.get("/download/{file_path:path}")
|
||||
async def download_video(_: Request, file_path: str):
|
||||
"""
|
||||
download video
|
||||
:param _: Request request
|
||||
:param file_path: video file path, eg: /cd1727ed-3473-42a2-a7da-4faafafec72b/final-1.mp4
|
||||
:return: video file
|
||||
"""
|
||||
tasks_dir = utils.task_dir()
|
||||
video_path = os.path.join(tasks_dir, file_path)
|
||||
file_path = pathlib.Path(video_path)
|
||||
filename = file_path.stem
|
||||
extension = file_path.suffix
|
||||
headers = {
|
||||
"Content-Disposition": f"attachment; filename={filename}{extension}"
|
||||
}
|
||||
return FileResponse(path=video_path, headers=headers, filename=f"{filename}{extension}",
|
||||
media_type=f'video/{extension[1:]}')
|
||||
|
||||
@ -5,6 +5,8 @@ from typing import List
|
||||
from loguru import logger
|
||||
from openai import OpenAI
|
||||
from openai import AzureOpenAI
|
||||
from openai.types.chat import ChatCompletion
|
||||
|
||||
from app.config import config
|
||||
|
||||
|
||||
@ -57,6 +59,11 @@ def _generate_response(prompt: str) -> str:
|
||||
api_key = config.app.get("qwen_api_key")
|
||||
model_name = config.app.get("qwen_model_name")
|
||||
base_url = "***"
|
||||
elif llm_provider == "cloudflare":
|
||||
api_key = config.app.get("cloudflare_api_key")
|
||||
model_name = config.app.get("cloudflare_model_name")
|
||||
account_id = config.app.get("cloudflare_account_id")
|
||||
base_url = "***"
|
||||
else:
|
||||
raise ValueError("llm_provider is not set, please set it in the config.toml file.")
|
||||
|
||||
@ -69,17 +76,31 @@ def _generate_response(prompt: str) -> str:
|
||||
|
||||
if llm_provider == "qwen":
|
||||
import dashscope
|
||||
from dashscope.api_entities.dashscope_response import GenerationResponse
|
||||
dashscope.api_key = api_key
|
||||
response = dashscope.Generation.call(
|
||||
model=model_name,
|
||||
messages=[{"role": "user", "content": prompt}]
|
||||
)
|
||||
content = response["output"]["text"]
|
||||
return content.replace("\n", "")
|
||||
if response:
|
||||
if isinstance(response, GenerationResponse):
|
||||
status_code = response.status_code
|
||||
if status_code != 200:
|
||||
raise Exception(
|
||||
f"[{llm_provider}] returned an error response: \"{response}\"")
|
||||
|
||||
content = response["output"]["text"]
|
||||
return content.replace("\n", "")
|
||||
else:
|
||||
raise Exception(
|
||||
f"[{llm_provider}] returned an invalid response: \"{response}\"")
|
||||
else:
|
||||
raise Exception(
|
||||
f"[{llm_provider}] returned an empty response")
|
||||
|
||||
if llm_provider == "gemini":
|
||||
import google.generativeai as genai
|
||||
genai.configure(api_key=api_key)
|
||||
genai.configure(api_key=api_key, transport='rest')
|
||||
|
||||
generation_config = {
|
||||
"temperature": 0.5,
|
||||
@ -111,10 +132,30 @@ def _generate_response(prompt: str) -> str:
|
||||
generation_config=generation_config,
|
||||
safety_settings=safety_settings)
|
||||
|
||||
convo = model.start_chat(history=[])
|
||||
try:
|
||||
response = model.generate_content(prompt)
|
||||
candidates = response.candidates
|
||||
generated_text = candidates[0].content.parts[0].text
|
||||
except (AttributeError, IndexError) as e:
|
||||
print("Gemini Error:", e)
|
||||
|
||||
convo.send_message(prompt)
|
||||
return convo.last.text
|
||||
return generated_text
|
||||
|
||||
if llm_provider == "cloudflare":
|
||||
import requests
|
||||
response = requests.post(
|
||||
f"https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/{model_name}",
|
||||
headers={"Authorization": f"Bearer {api_key}"},
|
||||
json={
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are a friendly assistant"},
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
}
|
||||
)
|
||||
result = response.json()
|
||||
logger.info(result)
|
||||
return result["result"]["response"]
|
||||
|
||||
if llm_provider == "azure":
|
||||
client = AzureOpenAI(
|
||||
@ -133,7 +174,15 @@ def _generate_response(prompt: str) -> str:
|
||||
messages=[{"role": "user", "content": prompt}]
|
||||
)
|
||||
if response:
|
||||
content = response.choices[0].message.content
|
||||
if isinstance(response, ChatCompletion):
|
||||
content = response.choices[0].message.content
|
||||
else:
|
||||
raise Exception(
|
||||
f"[{llm_provider}] returned an invalid response: \"{response}\", please check your network "
|
||||
f"connection and try again.")
|
||||
else:
|
||||
raise Exception(
|
||||
f"[{llm_provider}] returned an empty response, please check your network connection and try again.")
|
||||
|
||||
return content.replace("\n", "")
|
||||
|
||||
@ -149,9 +198,9 @@ Generate a script for a video, depending on the subject of the video.
|
||||
1. the script is to be returned as a string with the specified number of paragraphs.
|
||||
2. do not under any circumstance reference this prompt in your response.
|
||||
3. get straight to the point, don't start with unnecessary things like, "welcome to this video".
|
||||
4. you must not include any type of markdown or formatting in the script, never use a title.
|
||||
5. only return the raw content of the script.
|
||||
6. do not include "voiceover", "narrator" or similar indicators of what should be spoken at the beginning of each paragraph or line.
|
||||
4. you must not include any type of markdown or formatting in the script, never use a title.
|
||||
5. only return the raw content of the script.
|
||||
6. do not include "voiceover", "narrator" or similar indicators of what should be spoken at the beginning of each paragraph or line.
|
||||
7. you must not mention the prompt, or anything about the script itself. also, never talk about the amount of paragraphs or lines. just write the script.
|
||||
8. respond in the same language as the video subject.
|
||||
|
||||
|
||||
@ -5,6 +5,7 @@ from urllib.parse import urlencode
|
||||
import requests
|
||||
from typing import List
|
||||
from loguru import logger
|
||||
from moviepy.video.io.VideoFileClip import VideoFileClip
|
||||
|
||||
from app.config import config
|
||||
from app.models.schema import VideoAspect, VideoConcatMode, MaterialInfo
|
||||
@ -105,7 +106,19 @@ def save_video(video_url: str, save_dir: str = "") -> str:
|
||||
f.write(requests.get(video_url, proxies=proxies, verify=False, timeout=(60, 240)).content)
|
||||
|
||||
if os.path.exists(video_path) and os.path.getsize(video_path) > 0:
|
||||
return video_path
|
||||
try:
|
||||
clip = VideoFileClip(video_path)
|
||||
duration = clip.duration
|
||||
fps = clip.fps
|
||||
clip.close()
|
||||
if duration > 0 and fps > 0:
|
||||
return video_path
|
||||
except Exception as e:
|
||||
try:
|
||||
os.remove(video_path)
|
||||
except Exception as e:
|
||||
pass
|
||||
logger.warning(f"invalid video file: {video_path} => {str(e)}")
|
||||
return ""
|
||||
|
||||
|
||||
|
||||
@ -1,7 +1,5 @@
|
||||
import ast
|
||||
import json
|
||||
from abc import ABC, abstractmethod
|
||||
import redis
|
||||
from app.config import config
|
||||
from app.models import const
|
||||
|
||||
@ -46,8 +44,9 @@ class MemoryState(BaseState):
|
||||
# Redis state management
|
||||
class RedisState(BaseState):
|
||||
|
||||
def __init__(self, host='localhost', port=6379, db=0):
|
||||
self._redis = redis.StrictRedis(host=host, port=port, db=db)
|
||||
def __init__(self, host='localhost', port=6379, db=0, password=None):
|
||||
import redis
|
||||
self._redis = redis.StrictRedis(host=host, port=port, db=db, password=password)
|
||||
|
||||
def update_task(self, task_id: str, state: int = const.TASK_STATE_PROCESSING, progress: int = 0, **kwargs):
|
||||
progress = int(progress)
|
||||
@ -99,5 +98,6 @@ _enable_redis = config.app.get("enable_redis", False)
|
||||
_redis_host = config.app.get("redis_host", "localhost")
|
||||
_redis_port = config.app.get("redis_port", 6379)
|
||||
_redis_db = config.app.get("redis_db", 0)
|
||||
_redis_password = config.app.get("redis_password", None)
|
||||
|
||||
state = RedisState(host=_redis_host, port=_redis_port, db=_redis_db) if _enable_redis else MemoryState()
|
||||
state = RedisState(host=_redis_host, port=_redis_port, db=_redis_db, password=_redis_password) if _enable_redis else MemoryState()
|
||||
|
||||
@ -1,4 +1,5 @@
|
||||
import json
|
||||
import os.path
|
||||
import re
|
||||
|
||||
from faster_whisper import WhisperModel
|
||||
@ -17,8 +18,13 @@ model = None
|
||||
def create(audio_file, subtitle_file: str = ""):
|
||||
global model
|
||||
if not model:
|
||||
logger.info(f"loading model: {model_size}, device: {device}, compute_type: {compute_type}")
|
||||
model = WhisperModel(model_size_or_path=model_size,
|
||||
model_path = f"{utils.root_dir()}/models/whisper-{model_size}"
|
||||
model_bin_file = f"{model_path}/model.bin"
|
||||
if not os.path.isdir(model_path) or not os.path.isfile(model_bin_file):
|
||||
model_path = model_size
|
||||
|
||||
logger.info(f"loading model: {model_path}, device: {device}, compute_type: {compute_type}")
|
||||
model = WhisperModel(model_size_or_path=model_path,
|
||||
device=device,
|
||||
compute_type=compute_type)
|
||||
|
||||
|
||||
@ -4,7 +4,6 @@ from typing import List
|
||||
from PIL import ImageFont
|
||||
from loguru import logger
|
||||
from moviepy.editor import *
|
||||
from moviepy.video.fx.crop import crop
|
||||
from moviepy.video.tools.subtitles import SubtitlesClip
|
||||
|
||||
from app.models.schema import VideoAspect, VideoParams, VideoConcatMode
|
||||
@ -14,15 +13,16 @@ from app.utils import utils
|
||||
def get_bgm_file(bgm_type: str = "random", bgm_file: str = ""):
|
||||
if not bgm_type:
|
||||
return ""
|
||||
|
||||
if bgm_file and os.path.exists(bgm_file):
|
||||
return bgm_file
|
||||
|
||||
if bgm_type == "random":
|
||||
suffix = "*.mp3"
|
||||
song_dir = utils.song_dir()
|
||||
files = glob.glob(os.path.join(song_dir, suffix))
|
||||
return random.choice(files)
|
||||
|
||||
if os.path.exists(bgm_file):
|
||||
return bgm_file
|
||||
|
||||
return ""
|
||||
|
||||
|
||||
@ -41,6 +41,7 @@ def combine_videos(combined_video_path: str,
|
||||
req_dur = audio_duration / len(video_paths)
|
||||
req_dur = max_clip_duration
|
||||
logger.info(f"each clip will be maximum {req_dur} seconds long")
|
||||
output_dir = os.path.dirname(combined_video_path)
|
||||
|
||||
aspect = VideoAspect(video_aspect)
|
||||
video_width, video_height = aspect.to_resolution()
|
||||
@ -99,11 +100,18 @@ def combine_videos(combined_video_path: str,
|
||||
clips.append(clip)
|
||||
video_duration += clip.duration
|
||||
|
||||
final_clip = concatenate_videoclips(clips)
|
||||
final_clip = final_clip.set_fps(30)
|
||||
video_clip = concatenate_videoclips(clips)
|
||||
video_clip = video_clip.set_fps(30)
|
||||
logger.info(f"writing")
|
||||
# https://github.com/harry0703/MoneyPrinterTurbo/issues/111#issuecomment-2032354030
|
||||
final_clip.write_videofile(combined_video_path, threads=threads, logger=None)
|
||||
video_clip.write_videofile(filename=combined_video_path,
|
||||
threads=threads,
|
||||
logger=None,
|
||||
temp_audiofile_path=output_dir,
|
||||
audio_codec="aac",
|
||||
fps=30,
|
||||
)
|
||||
video_clip.close()
|
||||
logger.success(f"completed")
|
||||
return combined_video_path
|
||||
|
||||
@ -119,9 +127,9 @@ def wrap_text(text, max_width, font='Arial', fontsize=60):
|
||||
|
||||
width, height = get_text_size(text)
|
||||
if width <= max_width:
|
||||
return text
|
||||
return text, height
|
||||
|
||||
logger.warning(f"wrapping text, max_width: {max_width}, text_width: {width}, text: {text}")
|
||||
# logger.warning(f"wrapping text, max_width: {max_width}, text_width: {width}, text: {text}")
|
||||
|
||||
processed = True
|
||||
|
||||
@ -144,8 +152,9 @@ def wrap_text(text, max_width, font='Arial', fontsize=60):
|
||||
if processed:
|
||||
_wrapped_lines_ = [line.strip() for line in _wrapped_lines_]
|
||||
result = '\n'.join(_wrapped_lines_).strip()
|
||||
logger.warning(f"wrapped text: {result}")
|
||||
return result
|
||||
height = len(_wrapped_lines_) * height
|
||||
# logger.warning(f"wrapped text: {result}")
|
||||
return result, height
|
||||
|
||||
_wrapped_lines_ = []
|
||||
chars = list(text)
|
||||
@ -160,8 +169,9 @@ def wrap_text(text, max_width, font='Arial', fontsize=60):
|
||||
_txt_ = ''
|
||||
_wrapped_lines_.append(_txt_)
|
||||
result = '\n'.join(_wrapped_lines_).strip()
|
||||
logger.warning(f"wrapped text: {result}")
|
||||
return result
|
||||
height = len(_wrapped_lines_) * height
|
||||
# logger.warning(f"wrapped text: {result}")
|
||||
return result, height
|
||||
|
||||
|
||||
def generate_video(video_path: str,
|
||||
@ -179,6 +189,11 @@ def generate_video(video_path: str,
|
||||
logger.info(f" ③ subtitle: {subtitle_path}")
|
||||
logger.info(f" ④ output: {output_file}")
|
||||
|
||||
# https://github.com/harry0703/MoneyPrinterTurbo/issues/217
|
||||
# PermissionError: [WinError 32] The process cannot access the file because it is being used by another process: 'final-1.mp4.tempTEMP_MPY_wvf_snd.mp3'
|
||||
# write into the same directory as the output file
|
||||
output_dir = os.path.dirname(output_file)
|
||||
|
||||
font_path = ""
|
||||
if params.subtitle_enabled:
|
||||
if not params.font_name:
|
||||
@ -189,23 +204,15 @@ def generate_video(video_path: str,
|
||||
|
||||
logger.info(f"using font: {font_path}")
|
||||
|
||||
if params.subtitle_position == "top":
|
||||
position_height = video_height * 0.1
|
||||
elif params.subtitle_position == "bottom":
|
||||
position_height = video_height * 0.9
|
||||
else:
|
||||
position_height = "center"
|
||||
|
||||
def generator(txt, **kwargs):
|
||||
def create_text_clip(subtitle_item):
|
||||
phrase = subtitle_item[1]
|
||||
max_width = video_width * 0.9
|
||||
# logger.debug(f"rendering text: {txt}")
|
||||
wrapped_txt = wrap_text(txt,
|
||||
max_width=max_width,
|
||||
font=font_path,
|
||||
fontsize=params.font_size
|
||||
) # 调整max_width以适应你的视频
|
||||
|
||||
clip = TextClip(
|
||||
wrapped_txt, txt_height = wrap_text(phrase,
|
||||
max_width=max_width,
|
||||
font=font_path,
|
||||
fontsize=params.font_size
|
||||
)
|
||||
_clip = TextClip(
|
||||
wrapped_txt,
|
||||
font=font_path,
|
||||
fontsize=params.font_size,
|
||||
@ -215,52 +222,49 @@ def generate_video(video_path: str,
|
||||
stroke_width=params.stroke_width,
|
||||
print_cmd=False,
|
||||
)
|
||||
return clip
|
||||
duration = subtitle_item[0][1] - subtitle_item[0][0]
|
||||
_clip = _clip.set_start(subtitle_item[0][0])
|
||||
_clip = _clip.set_end(subtitle_item[0][1])
|
||||
_clip = _clip.set_duration(duration)
|
||||
if params.subtitle_position == "bottom":
|
||||
_clip = _clip.set_position(('center', video_height * 0.95 - _clip.h))
|
||||
elif params.subtitle_position == "top":
|
||||
_clip = _clip.set_position(('center', video_height * 0.1))
|
||||
else:
|
||||
_clip = _clip.set_position(('center', 'center'))
|
||||
return _clip
|
||||
|
||||
clips = [
|
||||
VideoFileClip(video_path),
|
||||
]
|
||||
video_clip = VideoFileClip(video_path)
|
||||
audio_clip = AudioFileClip(audio_path).volumex(params.voice_volume)
|
||||
|
||||
if subtitle_path and os.path.exists(subtitle_path):
|
||||
sub = SubtitlesClip(subtitles=subtitle_path, make_textclip=generator, encoding='utf-8')
|
||||
sub_clip = sub.set_position(lambda _t: ('center', position_height))
|
||||
clips.append(sub_clip)
|
||||
|
||||
result = CompositeVideoClip(clips)
|
||||
|
||||
audio = AudioFileClip(audio_path)
|
||||
try:
|
||||
audio = audio.volumex(params.voice_volume)
|
||||
except Exception as e:
|
||||
logger.warning(f"failed to set audio volume: {e}")
|
||||
|
||||
result = result.set_audio(audio)
|
||||
|
||||
temp_output_file = f"{output_file}.temp.mp4"
|
||||
logger.info(f"writing to temp file: {temp_output_file}")
|
||||
result.write_videofile(temp_output_file, threads=params.n_threads or 2, logger=None)
|
||||
|
||||
video_clip = VideoFileClip(temp_output_file)
|
||||
sub = SubtitlesClip(subtitles=subtitle_path, encoding='utf-8')
|
||||
text_clips = []
|
||||
for item in sub.subtitles:
|
||||
clip = create_text_clip(subtitle_item=item)
|
||||
text_clips.append(clip)
|
||||
video_clip = CompositeVideoClip([video_clip, *text_clips])
|
||||
|
||||
bgm_file = get_bgm_file(bgm_type=params.bgm_type, bgm_file=params.bgm_file)
|
||||
if bgm_file:
|
||||
logger.info(f"adding background music: {bgm_file}")
|
||||
# Add song to video at 30% volume using moviepy
|
||||
original_duration = video_clip.duration
|
||||
original_audio = video_clip.audio
|
||||
song_clip = AudioFileClip(bgm_file).set_fps(44100)
|
||||
# Set the volume of the song to 10% of the original volume
|
||||
song_clip = song_clip.volumex(params.bgm_volume)
|
||||
# Add the song to the video
|
||||
comp_audio = CompositeAudioClip([original_audio, song_clip])
|
||||
video_clip = video_clip.set_audio(comp_audio)
|
||||
video_clip = video_clip.set_fps(30)
|
||||
video_clip = video_clip.set_duration(original_duration)
|
||||
try:
|
||||
bgm_clip = (AudioFileClip(bgm_file)
|
||||
.volumex(params.bgm_volume)
|
||||
.audio_fadeout(3))
|
||||
bgm_clip = afx.audio_loop(bgm_clip, duration=video_clip.duration)
|
||||
audio_clip = CompositeAudioClip([audio_clip, bgm_clip])
|
||||
except Exception as e:
|
||||
logger.error(f"failed to add bgm: {str(e)}")
|
||||
|
||||
logger.info(f"encoding audio codec to aac")
|
||||
video_clip.write_videofile(output_file, audio_codec="aac", threads=params.n_threads or 2, logger=None)
|
||||
|
||||
os.remove(temp_output_file)
|
||||
video_clip = video_clip.set_audio(audio_clip)
|
||||
video_clip.write_videofile(output_file,
|
||||
audio_codec="aac",
|
||||
temp_audiofile_path=output_dir,
|
||||
threads=params.n_threads or 2,
|
||||
logger=None,
|
||||
fps=30,
|
||||
)
|
||||
video_clip.close()
|
||||
logger.success(f"completed")
|
||||
|
||||
|
||||
@ -269,28 +273,28 @@ if __name__ == "__main__":
|
||||
txt_zh = "测试长字段这是您的旅行技巧指南帮助您进行预算友好的冒险"
|
||||
font = utils.resource_dir() + "/fonts/STHeitiMedium.ttc"
|
||||
for txt in [txt_en, txt_zh]:
|
||||
t = wrap_text(text=txt, max_width=1000, font=font, fontsize=60)
|
||||
t, h = wrap_text(text=txt, max_width=1000, font=font, fontsize=60)
|
||||
print(t)
|
||||
|
||||
task_id = "69232dfa-f6c5-4b5e-80ba-be3098d3f930"
|
||||
task_id = "aa563149-a7ea-49c2-b39f-8c32cc225baf"
|
||||
task_dir = utils.task_dir(task_id)
|
||||
video_file = f"{task_dir}/combined-1.mp4"
|
||||
audio_file = f"{task_dir}/audio.mp3"
|
||||
subtitle_file = f"{task_dir}/subtitle.srt"
|
||||
output_file = f"{task_dir}/final.mp4"
|
||||
|
||||
video_paths = []
|
||||
for file in os.listdir(utils.storage_dir("test")):
|
||||
if file.endswith(".mp4"):
|
||||
video_paths.append(os.path.join(task_dir, file))
|
||||
|
||||
combine_videos(combined_video_path=video_file,
|
||||
audio_file=audio_file,
|
||||
video_paths=video_paths,
|
||||
video_aspect=VideoAspect.portrait,
|
||||
video_concat_mode=VideoConcatMode.random,
|
||||
max_clip_duration=5,
|
||||
threads=2)
|
||||
# video_paths = []
|
||||
# for file in os.listdir(utils.storage_dir("test")):
|
||||
# if file.endswith(".mp4"):
|
||||
# video_paths.append(os.path.join(utils.storage_dir("test"), file))
|
||||
#
|
||||
# combine_videos(combined_video_path=video_file,
|
||||
# audio_file=audio_file,
|
||||
# video_paths=video_paths,
|
||||
# video_aspect=VideoAspect.portrait,
|
||||
# video_concat_mode=VideoConcatMode.random,
|
||||
# max_clip_duration=5,
|
||||
# threads=2)
|
||||
|
||||
cfg = VideoParams()
|
||||
cfg.video_aspect = VideoAspect.portrait
|
||||
@ -300,14 +304,15 @@ if __name__ == "__main__":
|
||||
cfg.stroke_width = 1.5
|
||||
cfg.text_fore_color = "#FFFFFF"
|
||||
cfg.text_background_color = "transparent"
|
||||
cfg.bgm_type = "random"
|
||||
cfg.bgm_file = ""
|
||||
cfg.bgm_volume = 0.2
|
||||
cfg.bgm_volume = 1.0
|
||||
cfg.subtitle_enabled = True
|
||||
cfg.subtitle_position = "bottom"
|
||||
cfg.n_threads = 2
|
||||
cfg.paragraph_number = 1
|
||||
|
||||
cfg.voice_volume = 3.0
|
||||
cfg.voice_volume = 1.0
|
||||
|
||||
generate_video(video_path=video_file,
|
||||
audio_path=audio_file,
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
import asyncio
|
||||
import os
|
||||
import re
|
||||
from datetime import datetime
|
||||
from xml.sax.saxutils import unescape
|
||||
from edge_tts.submaker import mktimestamp
|
||||
from loguru import logger
|
||||
@ -8,10 +9,11 @@ from edge_tts import submaker, SubMaker
|
||||
import edge_tts
|
||||
from moviepy.video.tools import subtitles
|
||||
|
||||
from app.config import config
|
||||
from app.utils import utils
|
||||
|
||||
|
||||
def get_all_voices(filter_locals=None) -> list[str]:
|
||||
def get_all_azure_voices(filter_locals=None) -> list[str]:
|
||||
if filter_locals is None:
|
||||
filter_locals = ["zh-CN", "en-US", "zh-HK", "zh-TW"]
|
||||
voices_str = """
|
||||
@ -956,6 +958,34 @@ Gender: Female
|
||||
|
||||
Name: zu-ZA-ThembaNeural
|
||||
Gender: Male
|
||||
|
||||
|
||||
Name: en-US-AvaMultilingualNeural-V2
|
||||
Gender: Female
|
||||
|
||||
Name: en-US-AndrewMultilingualNeural-V2
|
||||
Gender: Male
|
||||
|
||||
Name: en-US-EmmaMultilingualNeural-V2
|
||||
Gender: Female
|
||||
|
||||
Name: en-US-BrianMultilingualNeural-V2
|
||||
Gender: Male
|
||||
|
||||
Name: de-DE-FlorianMultilingualNeural-V2
|
||||
Gender: Male
|
||||
|
||||
Name: de-DE-SeraphinaMultilingualNeural-V2
|
||||
Gender: Female
|
||||
|
||||
Name: fr-FR-RemyMultilingualNeural-V2
|
||||
Gender: Male
|
||||
|
||||
Name: fr-FR-VivienneMultilingualNeural-V2
|
||||
Gender: Female
|
||||
|
||||
Name: zh-CN-XiaoxiaoMultilingualNeural-V2
|
||||
Gender: Female
|
||||
""".strip()
|
||||
voices = []
|
||||
name = ''
|
||||
@ -986,11 +1016,26 @@ Gender: Male
|
||||
def parse_voice_name(name: str):
|
||||
# zh-CN-XiaoyiNeural-Female
|
||||
# zh-CN-YunxiNeural-Male
|
||||
# zh-CN-XiaoxiaoMultilingualNeural-V2-Female
|
||||
name = name.replace("-Female", "").replace("-Male", "").strip()
|
||||
return name
|
||||
|
||||
|
||||
def is_azure_v2_voice(voice_name: str):
|
||||
voice_name = parse_voice_name(voice_name)
|
||||
print(voice_name)
|
||||
if voice_name.endswith("-V2"):
|
||||
return voice_name.replace("-V2", "").strip()
|
||||
return ""
|
||||
|
||||
|
||||
def tts(text: str, voice_name: str, voice_file: str) -> [SubMaker, None]:
|
||||
if is_azure_v2_voice(voice_name):
|
||||
return azure_tts_v2(text, voice_name, voice_file)
|
||||
return azure_tts_v1(text, voice_name, voice_file)
|
||||
|
||||
|
||||
def azure_tts_v1(text: str, voice_name: str, voice_file: str) -> [SubMaker, None]:
|
||||
text = text.strip()
|
||||
for i in range(3):
|
||||
try:
|
||||
@ -1019,14 +1064,82 @@ def tts(text: str, voice_name: str, voice_file: str) -> [SubMaker, None]:
|
||||
return None
|
||||
|
||||
|
||||
def create_subtitle(sub_maker: submaker.SubMaker, text: str, subtitle_file: str):
|
||||
"""
|
||||
优化字幕文件
|
||||
1. 将字幕文件按照标点符号分割成多行
|
||||
2. 逐行匹配字幕文件中的文本
|
||||
3. 生成新的字幕文件
|
||||
"""
|
||||
text = text.replace("\n", " ")
|
||||
def azure_tts_v2(text: str, voice_name: str, voice_file: str) -> [SubMaker, None]:
|
||||
voice_name = is_azure_v2_voice(voice_name)
|
||||
if not voice_name:
|
||||
logger.error(f"invalid voice name: {voice_name}")
|
||||
raise ValueError(f"invalid voice name: {voice_name}")
|
||||
text = text.strip()
|
||||
|
||||
def _format_duration_to_offset(duration) -> int:
|
||||
if isinstance(duration, str):
|
||||
time_obj = datetime.strptime(duration, "%H:%M:%S.%f")
|
||||
milliseconds = (time_obj.hour * 3600000) + (time_obj.minute * 60000) + (time_obj.second * 1000) + (
|
||||
time_obj.microsecond // 1000)
|
||||
return milliseconds * 10000
|
||||
|
||||
if isinstance(duration, int):
|
||||
return duration
|
||||
|
||||
return 0
|
||||
|
||||
for i in range(3):
|
||||
try:
|
||||
logger.info(f"start, voice name: {voice_name}, try: {i + 1}")
|
||||
|
||||
import azure.cognitiveservices.speech as speechsdk
|
||||
|
||||
sub_maker = SubMaker()
|
||||
|
||||
def speech_synthesizer_word_boundary_cb(evt: speechsdk.SessionEventArgs):
|
||||
# print('WordBoundary event:')
|
||||
# print('\tBoundaryType: {}'.format(evt.boundary_type))
|
||||
# print('\tAudioOffset: {}ms'.format((evt.audio_offset + 5000)))
|
||||
# print('\tDuration: {}'.format(evt.duration))
|
||||
# print('\tText: {}'.format(evt.text))
|
||||
# print('\tTextOffset: {}'.format(evt.text_offset))
|
||||
# print('\tWordLength: {}'.format(evt.word_length))
|
||||
|
||||
duration = _format_duration_to_offset(str(evt.duration))
|
||||
offset = _format_duration_to_offset(evt.audio_offset)
|
||||
sub_maker.subs.append(evt.text)
|
||||
sub_maker.offset.append((offset, offset + duration))
|
||||
|
||||
# Creates an instance of a speech config with specified subscription key and service region.
|
||||
speech_key = config.azure.get("speech_key", "")
|
||||
service_region = config.azure.get("speech_region", "")
|
||||
audio_config = speechsdk.audio.AudioOutputConfig(filename=voice_file, use_default_speaker=True)
|
||||
speech_config = speechsdk.SpeechConfig(subscription=speech_key,
|
||||
region=service_region)
|
||||
speech_config.speech_synthesis_voice_name = voice_name
|
||||
# speech_config.set_property(property_id=speechsdk.PropertyId.SpeechServiceResponse_RequestSentenceBoundary,
|
||||
# value='true')
|
||||
speech_config.set_property(property_id=speechsdk.PropertyId.SpeechServiceResponse_RequestWordBoundary,
|
||||
value='true')
|
||||
|
||||
speech_config.set_speech_synthesis_output_format(
|
||||
speechsdk.SpeechSynthesisOutputFormat.Audio48Khz192KBitRateMonoMp3)
|
||||
speech_synthesizer = speechsdk.SpeechSynthesizer(audio_config=audio_config,
|
||||
speech_config=speech_config)
|
||||
speech_synthesizer.synthesis_word_boundary.connect(speech_synthesizer_word_boundary_cb)
|
||||
|
||||
result = speech_synthesizer.speak_text_async(text).get()
|
||||
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
|
||||
logger.success(f"azure v2 speech synthesis succeeded: {voice_file}")
|
||||
return sub_maker
|
||||
elif result.reason == speechsdk.ResultReason.Canceled:
|
||||
cancellation_details = result.cancellation_details
|
||||
logger.error(f"azure v2 speech synthesis canceled: {cancellation_details.reason}")
|
||||
if cancellation_details.reason == speechsdk.CancellationReason.Error:
|
||||
logger.error(f"azure v2 speech synthesis error: {cancellation_details.error_details}")
|
||||
logger.info(f"completed, output file: {voice_file}")
|
||||
except Exception as e:
|
||||
logger.error(f"failed, error: {str(e)}")
|
||||
return None
|
||||
|
||||
|
||||
def _format_text(text: str) -> str:
|
||||
# text = text.replace("\n", " ")
|
||||
text = text.replace("[", " ")
|
||||
text = text.replace("]", " ")
|
||||
text = text.replace("(", " ")
|
||||
@ -1034,6 +1147,18 @@ def create_subtitle(sub_maker: submaker.SubMaker, text: str, subtitle_file: str)
|
||||
text = text.replace("{", " ")
|
||||
text = text.replace("}", " ")
|
||||
text = text.strip()
|
||||
return text
|
||||
|
||||
|
||||
def create_subtitle(sub_maker: submaker.SubMaker, text: str, subtitle_file: str):
|
||||
"""
|
||||
优化字幕文件
|
||||
1. 将字幕文件按照标点符号分割成多行
|
||||
2. 逐行匹配字幕文件中的文本
|
||||
3. 生成新的字幕文件
|
||||
"""
|
||||
|
||||
text = _format_text(text)
|
||||
|
||||
def formatter(idx: int, start_time: float, end_time: float, sub_text: str) -> str:
|
||||
"""
|
||||
@ -1125,8 +1250,12 @@ def get_audio_duration(sub_maker: submaker.SubMaker):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
voices = get_all_voices()
|
||||
print(voices)
|
||||
voice_name = "zh-CN-XiaoxiaoMultilingualNeural-V2-Female"
|
||||
voice_name = parse_voice_name(voice_name)
|
||||
voice_name = is_azure_v2_voice(voice_name)
|
||||
print(voice_name)
|
||||
|
||||
voices = get_all_azure_voices()
|
||||
print(len(voices))
|
||||
|
||||
|
||||
@ -1134,6 +1263,7 @@ if __name__ == "__main__":
|
||||
temp_dir = utils.storage_dir("temp")
|
||||
|
||||
voice_names = [
|
||||
"zh-CN-XiaoxiaoMultilingualNeural",
|
||||
# 女性
|
||||
"zh-CN-XiaoxiaoNeural",
|
||||
"zh-CN-XiaoyiNeural",
|
||||
@ -1156,10 +1286,28 @@ if __name__ == "__main__":
|
||||
"""
|
||||
|
||||
text = "[Opening scene: A sunny day in a suburban neighborhood. A young boy named Alex, around 8 years old, is playing in his front yard with his loyal dog, Buddy.]\n\n[Camera zooms in on Alex as he throws a ball for Buddy to fetch. Buddy excitedly runs after it and brings it back to Alex.]\n\nAlex: Good boy, Buddy! You're the best dog ever!\n\n[Buddy barks happily and wags his tail.]\n\n[As Alex and Buddy continue playing, a series of potential dangers loom nearby, such as a stray dog approaching, a ball rolling towards the street, and a suspicious-looking stranger walking by.]\n\nAlex: Uh oh, Buddy, look out!\n\n[Buddy senses the danger and immediately springs into action. He barks loudly at the stray dog, scaring it away. Then, he rushes to retrieve the ball before it reaches the street and gently nudges it back towards Alex. Finally, he stands protectively between Alex and the stranger, growling softly to warn them away.]\n\nAlex: Wow, Buddy, you're like my superhero!\n\n[Just as Alex and Buddy are about to head inside, they hear a loud crash from a nearby construction site. They rush over to investigate and find a pile of rubble blocking the path of a kitten trapped underneath.]\n\nAlex: Oh no, Buddy, we have to help!\n\n[Buddy barks in agreement and together they work to carefully move the rubble aside, allowing the kitten to escape unharmed. The kitten gratefully nuzzles against Buddy, who responds with a friendly lick.]\n\nAlex: We did it, Buddy! We saved the day again!\n\n[As Alex and Buddy walk home together, the sun begins to set, casting a warm glow over the neighborhood.]\n\nAlex: Thanks for always being there to watch over me, Buddy. You're not just my dog, you're my best friend.\n\n[Buddy barks happily and nuzzles against Alex as they disappear into the sunset, ready to face whatever adventures tomorrow may bring.]\n\n[End scene.]"
|
||||
|
||||
text = "大家好，我是乔哥，一个想帮你把信用卡全部还清的家伙！\n今天我们要聊的是信用卡的取现功能。\n你是不是也曾经因为一时的资金紧张，而拿着信用卡到ATM机取现？如果是，那你得好好看看这个视频了。\n现在都2024年了，我以为现在不会再有人用信用卡取现功能了。前几天一个粉丝发来一张图片，取现1万。\n信用卡取现有三个弊端。\n一，信用卡取现功能代价可不小。会先收取一个取现手续费，比如这个粉丝，取现1万，按2.5%收取手续费，收取了250元。\n二，信用卡正常消费有最长56天的免息期，但取现不享受免息期。从取现那一天开始，每天按照万5收取利息，这个粉丝用了11天，收取了55元利息。\n三，频繁的取现行为，银行会认为你资金紧张，会被标记为高风险用户，影响你的综合评分和额度。\n那么，如果你资金紧张了，该怎么办呢？\n乔哥给你支一招，用破思机摩擦信用卡，只需要少量的手续费，而且还可以享受最长56天的免息期。\n最后，如果你对玩卡感兴趣，可以找乔哥领取一本《卡神秘籍》，用卡过程中遇到任何疑惑，也欢迎找乔哥交流。\n别忘了，关注乔哥，回复用卡技巧，免费领取《2024用卡技巧》，让我们一起成为用卡高手！"
|
||||
|
||||
text = """
|
||||
2023全年业绩速览
|
||||
公司全年累计实现营业收入1476.94亿元，同比增长19.01%，归母净利润747.34亿元，同比增长19.16%。EPS达到59.49元。第四季度单季，营业收入444.25亿元，同比增长20.26%，环比增长31.86%；归母净利润218.58亿元，同比增长19.33%，环比增长29.37%。这一阶段
|
||||
的业绩表现不仅突显了公司的增长动力和盈利能力，也反映出公司在竞争激烈的市场环境中保持了良好的发展势头。
|
||||
2023年Q4业绩速览
|
||||
第四季度，营业收入贡献主要增长点；销售费用高增致盈利能力承压；税金同比上升27%，扰动净利率表现。
|
||||
业绩解读
|
||||
利润方面，2023全年贵州茅台，>归母净利润增速为19%，其中营业收入正贡献18%，营业成本正贡献百分之一，管理费用正贡献百分之一点四。(注：归母净利润增速值=营业收入增速+各科目贡献，展示贡献/拖累的前四名科目，且要求贡献值/净利润增速>15%)
|
||||
"""
|
||||
text = "静夜思是唐代诗人李白创作的一首五言古诗。这首诗描绘了诗人在寂静的夜晚，看到窗前的明月，不禁想起远方的家乡和亲人"
|
||||
|
||||
text = _format_text(text)
|
||||
lines = utils.split_string_by_punctuations(text)
|
||||
print(lines)
|
||||
|
||||
for voice_name in voice_names:
|
||||
voice_file = f"{temp_dir}/tts-{voice_name}.mp3"
|
||||
subtitle_file = f"{temp_dir}/tts.mp3.srt"
|
||||
sub_maker = tts(text=text, voice_name=voice_name, voice_file=voice_file)
|
||||
sub_maker = azure_tts_v2(text=text, voice_name=voice_name, voice_file=voice_file)
|
||||
create_subtitle(sub_maker=sub_maker, text=text, subtitle_file=subtitle_file)
|
||||
audio_duration = get_audio_duration(sub_maker)
|
||||
print(f"voice: {voice_name}, audio duration: {audio_duration}s")
|
||||
|
||||
@ -163,12 +163,34 @@ def str_contains_punctuation(word):
|
||||
def split_string_by_punctuations(s):
|
||||
result = []
|
||||
txt = ""
|
||||
for char in s:
|
||||
|
||||
previous_char = ""
|
||||
next_char = ""
|
||||
for i in range(len(s)):
|
||||
char = s[i]
|
||||
if char == "\n":
|
||||
result.append(txt.strip())
|
||||
txt = ""
|
||||
continue
|
||||
|
||||
if i > 0:
|
||||
previous_char = s[i - 1]
|
||||
if i < len(s) - 1:
|
||||
next_char = s[i + 1]
|
||||
|
||||
if char == "." and previous_char.isdigit() and next_char.isdigit():
|
||||
# 取现1万，按2.5%收取手续费, 2.5 中的 . 不能作为换行标记
|
||||
txt += char
|
||||
continue
|
||||
|
||||
if char not in const.PUNCTUATIONS:
|
||||
txt += char
|
||||
else:
|
||||
result.append(txt.strip())
|
||||
txt = ""
|
||||
result.append(txt.strip())
|
||||
# filter empty string
|
||||
result = list(filter(None, result))
|
||||
return result
|
||||
|
||||
|
||||
|
||||
@ -161,4 +161,10 @@
|
||||
### Example: "http://user:pass@proxy:1234"
|
||||
### Doc: https://requests.readthedocs.io/en/latest/user/advanced/#proxies
|
||||
# http = "http://10.10.1.10:3128"
|
||||
# https = "http://10.10.1.10:1080"
|
||||
# https = "http://10.10.1.10:1080"
|
||||
|
||||
[azure]
|
||||
# Azure Speech API Key
|
||||
# Get your API key at https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices
|
||||
speech_key=""
|
||||
speech_region=""
|
||||
@ -1,8 +1,5 @@
|
||||
version: "3"
|
||||
|
||||
x-common-volumes: &common-volumes
|
||||
- ./config.toml:/MoneyPrinterTurbo/config.toml
|
||||
- ./storage:/MoneyPrinterTurbo/storage
|
||||
- ./:/MoneyPrinterTurbo
|
||||
|
||||
services:
|
||||
webui:
|
||||
@ -12,7 +9,7 @@ services:
|
||||
container_name: "webui"
|
||||
ports:
|
||||
- "8501:8501"
|
||||
command: ["streamlit", "run", "./webui/Main.py","--browser.serverAddress=0.0.0.0","--server.enableCORS=True","--browser.gatherUsageStats=False"]
|
||||
command: [ "streamlit", "run", "./webui/Main.py","--browser.serverAddress=127.0.0.1","--server.enableCORS=True","--browser.gatherUsageStats=False" ]
|
||||
volumes: *common-volumes
|
||||
restart: always
|
||||
api:
|
||||
|
||||
BIN
docs/picwish.jpg
Normal file
BIN
docs/picwish.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 178 KiB |
BIN
docs/wechat-03.jpg
Normal file
BIN
docs/wechat-03.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 165 KiB |
@ -16,4 +16,10 @@ g4f~=0.2.5.4
|
||||
dashscope~=1.15.0
|
||||
google.generativeai~=0.4.1
|
||||
python-multipart~=0.0.9
|
||||
redis==5.0.3
|
||||
redis==5.0.3
|
||||
# if you use pillow~=10.3.0, you will get "PIL.Image' has no attribute 'ANTIALIAS'" error when resize video
|
||||
# please install opencv-python to fix "PIL.Image' has no attribute 'ANTIALIAS'" error
|
||||
opencv-python
|
||||
# for azure speech
|
||||
# https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/9-more-realistic-ai-voices-for-conversations-now-generally/ba-p/4099471
|
||||
azure-cognitiveservices-speech~=1.37.0
|
||||
@ -1,2 +1,7 @@
|
||||
@echo off
|
||||
set CURRENT_DIR=%CD%
|
||||
echo ***** Current directory: %CURRENT_DIR% *****
|
||||
set PYTHONPATH=%CURRENT_DIR%
|
||||
|
||||
rem set HF_ENDPOINT=https://hf-mirror.com
|
||||
streamlit run .\webui\Main.py --browser.gatherUsageStats=False --server.enableCORS=True
|
||||
@ -1,5 +1,6 @@
|
||||
import sys
|
||||
import os
|
||||
import time
|
||||
|
||||
# Add the root directory of the project to the system path to allow importing modules from the project
|
||||
root_dir = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
|
||||
@ -38,7 +39,7 @@ hide_streamlit_style = """
|
||||
<style>#root > div:nth-child(1) > div > div > div > div > section > div {padding-top: 0rem;}</style>
|
||||
"""
|
||||
st.markdown(hide_streamlit_style, unsafe_allow_html=True)
|
||||
st.title("MoneyPrinterTurbo")
|
||||
st.title(f"MoneyPrinterTurbo v{config.project_version}")
|
||||
|
||||
font_dir = os.path.join(root_dir, "resource", "fonts")
|
||||
song_dir = os.path.join(root_dir, "resource", "songs")
|
||||
@ -62,6 +63,7 @@ def get_all_fonts():
|
||||
for file in files:
|
||||
if file.endswith(".ttf") or file.endswith(".ttc"):
|
||||
fonts.append(file)
|
||||
fonts.sort()
|
||||
return fonts
|
||||
|
||||
|
||||
@ -164,7 +166,6 @@ with st.expander(tr("Basic Settings"), expanded=False):
|
||||
code = selected_language.split(" - ")[0].strip()
|
||||
st.session_state['ui_language'] = code
|
||||
config.ui['language'] = code
|
||||
config.save_config()
|
||||
|
||||
with middle_config_panel:
|
||||
# openai
|
||||
@ -175,7 +176,7 @@ with st.expander(tr("Basic Settings"), expanded=False):
|
||||
# qwen (通义千问)
|
||||
# gemini
|
||||
# ollama
|
||||
llm_providers = ['OpenAI', 'Moonshot', 'Azure', 'Qwen', 'Gemini', 'Ollama', 'G4f', 'OneAPI']
|
||||
llm_providers = ['OpenAI', 'Moonshot', 'Azure', 'Qwen', 'Gemini', 'Ollama', 'G4f', 'OneAPI', "Cloudflare"]
|
||||
saved_llm_provider = config.app.get("llm_provider", "OpenAI").lower()
|
||||
saved_llm_provider_index = 0
|
||||
for i, provider in enumerate(llm_providers):
|
||||
@ -190,6 +191,7 @@ with st.expander(tr("Basic Settings"), expanded=False):
|
||||
llm_api_key = config.app.get(f"{llm_provider}_api_key", "")
|
||||
llm_base_url = config.app.get(f"{llm_provider}_base_url", "")
|
||||
llm_model_name = config.app.get(f"{llm_provider}_model_name", "")
|
||||
llm_account_id = config.app.get(f"{llm_provider}_account_id", "")
|
||||
st_llm_api_key = st.text_input(tr("API Key"), value=llm_api_key, type="password")
|
||||
st_llm_base_url = st.text_input(tr("Base Url"), value=llm_base_url)
|
||||
st_llm_model_name = st.text_input(tr("Model Name"), value=llm_model_name)
|
||||
@ -200,7 +202,10 @@ with st.expander(tr("Basic Settings"), expanded=False):
|
||||
if st_llm_model_name:
|
||||
config.app[f"{llm_provider}_model_name"] = st_llm_model_name
|
||||
|
||||
config.save_config()
|
||||
if llm_provider == 'cloudflare':
|
||||
st_llm_account_id = st.text_input(tr("Account ID"), value=llm_account_id)
|
||||
if st_llm_account_id:
|
||||
config.app[f"{llm_provider}_account_id"] = st_llm_account_id
|
||||
|
||||
with right_config_panel:
|
||||
pexels_api_keys = config.app.get("pexels_api_keys", [])
|
||||
@ -212,7 +217,6 @@ with st.expander(tr("Basic Settings"), expanded=False):
|
||||
pexels_api_key = pexels_api_key.replace(" ", "")
|
||||
if pexels_api_key:
|
||||
config.app["pexels_api_keys"] = pexels_api_key.split(",")
|
||||
config.save_config()
|
||||
|
||||
panel = st.columns(3)
|
||||
left_panel = panel[0]
|
||||
@ -295,20 +299,20 @@ with middle_panel:
|
||||
index=0)
|
||||
with st.container(border=True):
|
||||
st.write(tr("Audio Settings"))
|
||||
voices = voice.get_all_voices(filter_locals=["zh-CN", "zh-HK", "zh-TW", "de-DE", "en-US"])
|
||||
voices = voice.get_all_azure_voices(filter_locals=["zh-CN", "zh-HK", "zh-TW", "de-DE", "en-US", "fr-FR"])
|
||||
friendly_names = {
|
||||
voice: voice.
|
||||
v: v.
|
||||
replace("Female", tr("Female")).
|
||||
replace("Male", tr("Male")).
|
||||
replace("Neural", "") for
|
||||
voice in voices}
|
||||
v in voices}
|
||||
saved_voice_name = config.ui.get("voice_name", "")
|
||||
saved_voice_name_index = 0
|
||||
if saved_voice_name in friendly_names:
|
||||
saved_voice_name_index = list(friendly_names.keys()).index(saved_voice_name)
|
||||
else:
|
||||
for i, voice in enumerate(voices):
|
||||
if voice.lower().startswith(st.session_state['ui_language'].lower()):
|
||||
for i, v in enumerate(voices):
|
||||
if v.lower().startswith(st.session_state['ui_language'].lower()):
|
||||
saved_voice_name_index = i
|
||||
break
|
||||
|
||||
@ -319,7 +323,13 @@ with middle_panel:
|
||||
voice_name = list(friendly_names.keys())[list(friendly_names.values()).index(selected_friendly_name)]
|
||||
params.voice_name = voice_name
|
||||
config.ui['voice_name'] = voice_name
|
||||
config.save_config()
|
||||
if voice.is_azure_v2_voice(voice_name):
|
||||
saved_azure_speech_region = config.azure.get(f"speech_region", "")
|
||||
saved_azure_speech_key = config.azure.get(f"speech_key", "")
|
||||
azure_speech_region = st.text_input(tr("Speech Region"), value=saved_azure_speech_region)
|
||||
azure_speech_key = st.text_input(tr("Speech Key"), value=saved_azure_speech_key, type="password")
|
||||
config.azure["speech_region"] = azure_speech_region
|
||||
config.azure["speech_key"] = azure_speech_key
|
||||
|
||||
params.voice_volume = st.selectbox(tr("Speech Volume"),
|
||||
options=[0.6, 0.8, 1.0, 1.2, 1.5, 2.0, 3.0, 4.0, 5.0], index=2)
|
||||
@ -356,7 +366,6 @@ with right_panel:
|
||||
saved_font_name_index = font_names.index(saved_font_name)
|
||||
params.font_name = st.selectbox(tr("Font"), font_names, index=saved_font_name_index)
|
||||
config.ui['font_name'] = params.font_name
|
||||
config.save_config()
|
||||
|
||||
subtitle_positions = [
|
||||
(tr("Top"), "top"),
|
||||
@ -439,3 +448,5 @@ if start_button:
|
||||
open_task_folder(task_id)
|
||||
logger.info(tr("Video Generation Completed"))
|
||||
scroll_to_bottom()
|
||||
|
||||
config.save_config()
|
||||
|
||||
@ -23,6 +23,8 @@
|
||||
"Number of Videos Generated Simultaneously": "Anzahl der parallel generierten Videos",
|
||||
"Audio Settings": "**Audio Einstellungen**",
|
||||
"Speech Synthesis": "Sprachausgabe",
|
||||
"Speech Region": "Region(:red[Required，[Get Region](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
|
||||
"Speech Key": "API Key(:red[Required，[Get API Key](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
|
||||
"Speech Volume": "Lautstärke der Sprachausgabe",
|
||||
"Male": "Männlich",
|
||||
"Female": "Weiblich",
|
||||
@ -58,6 +60,6 @@
|
||||
"Model Name": "Model Name",
|
||||
"Please Enter the LLM API Key": "Please Enter the **LLM API Key**",
|
||||
"Please Enter the Pexels API Key": "Please Enter the **Pexels API Key**",
|
||||
"Get Help": "If you need help, or have any questions, you can join discord for help: https://harryai.cc/moneyprinterturbo"
|
||||
"Get Help": "If you need help, or have any questions, you can join discord for help: https://harryai.cc"
|
||||
}
|
||||
}
|
||||
@ -23,6 +23,8 @@
|
||||
"Number of Videos Generated Simultaneously": "Number of Videos Generated Simultaneously",
|
||||
"Audio Settings": "**Audio Settings**",
|
||||
"Speech Synthesis": "Speech Synthesis Voice",
|
||||
"Speech Region": "Region(:red[Required，[Get Region](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
|
||||
"Speech Key": "API Key(:red[Required，[Get API Key](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
|
||||
"Speech Volume": "Speech Volume (1.0 represents 100%)",
|
||||
"Male": "Male",
|
||||
"Female": "Female",
|
||||
@ -55,9 +57,10 @@
|
||||
"LLM Provider": "LLM Provider",
|
||||
"API Key": "API Key (:red[Required])",
|
||||
"Base Url": "Base Url",
|
||||
"Account ID": "Account ID (Get from Cloudflare dashboard)",
|
||||
"Model Name": "Model Name",
|
||||
"Please Enter the LLM API Key": "Please Enter the **LLM API Key**",
|
||||
"Please Enter the Pexels API Key": "Please Enter the **Pexels API Key**",
|
||||
"Get Help": "If you need help, or have any questions, you can join discord for help: https://harryai.cc/moneyprinterturbo"
|
||||
"Get Help": "If you need help, or have any questions, you can join discord for help: https://harryai.cc"
|
||||
}
|
||||
}
|
||||
@ -23,6 +23,8 @@
|
||||
"Number of Videos Generated Simultaneously": "同时生成视频数量",
|
||||
"Audio Settings": "**音频设置**",
|
||||
"Speech Synthesis": "朗读声音（:red[尽量与文案语言保持一致]）",
|
||||
"Speech Region": "服务区域(:red[必填，[点击获取](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
|
||||
"Speech Key": "API Key(:red[必填，[点击获取](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
|
||||
"Speech Volume": "朗读音量（1.0表示100%）",
|
||||
"Male": "男性",
|
||||
"Female": "女性",
|
||||
@ -55,9 +57,10 @@
|
||||
"LLM Provider": "大模型提供商",
|
||||
"API Key": "API Key (:red[必填，需要到大模型提供商的后台申请])",
|
||||
"Base Url": "Base Url (可选)",
|
||||
"Account ID": "账户ID (Cloudflare的dash面板url中获取)",
|
||||
"Model Name": "模型名称 (:blue[需要到大模型提供商的后台确认被授权的模型名称])",
|
||||
"Please Enter the LLM API Key": "请先填写大模型 **API Key**",
|
||||
"Please Enter the Pexels API Key": "请先填写 **Pexels API Key**",
|
||||
"Get Help": "有任何问题或建议，可以加入 **微信群** 求助或讨论：https://harryai.cc/moneyprinterturbo"
|
||||
"Get Help": "有任何问题或建议，可以加入 **微信群** 求助或讨论：https://harryai.cc"
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user