Merge branch 'main' of https://github.com/harry0703/MoneyPrinterTurbo into main

README.md

@@ -66,6 +66,9 @@
 - [ ] 支持更多的语音合成服务商，比如 OpenAI TTS, Azure TTS
 - [ ] 自动上传到YouTube平台
 
+## 交流讨论 💬
+<img src="docs/wechat-01.jpg" width="300">
+
 ## 视频演示 📺
 
 ### 竖屏 9:16
@@ -102,8 +105,17 @@
 </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
+
 ## 安装部署 📥
 
+> 不想部署的可以直接下载安装包，解压直接使用
+- **Windows** 版本下载地址
+  - 百度网盘: https://pan.baidu.com/s/1BB3SGtAFTytzFLS5t2d8Gg?pwd=5bry
+
+### 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
 
@@ -375,14 +387,6 @@ 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 📚
 

app/config/config.py

@@ -53,7 +53,7 @@ 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", "1.1.0")
 reload_debug = False
 
 imagemagick_path = app.get("imagemagick_path", "")

app/services/llm.py

@@ -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
 
 
@@ -154,7 +156,15 @@ def _generate_response(prompt: str) -> str:
             messages=[{"role": "user", "content": prompt}]
         )
         if response:
+            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", "")
 

app/services/subtitle.py

@@ -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_path = f"{utils.root_dir()}/models/whisper-{model_size}"
-        model = WhisperModel(model_size_or_path=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)
 

app/services/video.py

@@ -124,7 +124,7 @@ 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}")
 
@@ -149,8 +149,9 @@ 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()
+        height = len(_wrapped_lines_) * height
         logger.warning(f"wrapped text: {result}")
-        return result
+        return result, height
 
     _wrapped_lines_ = []
     chars = list(text)
@@ -165,8 +166,9 @@ def wrap_text(text, max_width, font='Arial', fontsize=60):
             _txt_ = ''
     _wrapped_lines_.append(_txt_)
     result = '\n'.join(_wrapped_lines_).strip()
+    height = len(_wrapped_lines_) * height
     logger.warning(f"wrapped text: {result}")
-    return result
+    return result, height
 
 
 def generate_video(video_path: str,
@@ -199,23 +201,15 @@ def generate_video(video_path: str,
 
         logger.info(f"using font: {font_path}")
 
-    if params.subtitle_position == "top":
+    def create_text_clip(subtitle_item):
-        position_height = video_height * 0.1
+        phrase = subtitle_item[1]
-    elif params.subtitle_position == "bottom":
-        position_height = video_height * 0.9
-    else:
-        position_height = "center"
-
-    def generator(txt, **kwargs):
         max_width = video_width * 0.9
-        # logger.debug(f"rendering text: {txt}")
+        wrapped_txt, txt_height = wrap_text(phrase,
-        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(
-        clip = TextClip(
             wrapped_txt,
             font=font_path,
             fontsize=params.font_size,
@@ -225,15 +219,28 @@ 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
 
     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 = SubtitlesClip(subtitles=subtitle_path, encoding='utf-8')
-        sub_clip = sub.set_position(lambda _t: ('center', position_height))
+        text_clips = []
-        video_clip = CompositeVideoClip([video_clip, sub_clip])
+        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:
@@ -258,7 +265,7 @@ 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 = "aa563149-a7ea-49c2-b39f-8c32cc225baf"

webui/Main.py

@@ -38,7 +38,7 @@ 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")

webui/i18n/de.json

@@ -58,6 +58,6 @@
     "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"
   }
 }

webui/i18n/en.json

@@ -59,6 +59,6 @@
     "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"
   }
 }

webui/i18n/zh.json

@@ -59,6 +59,6 @@
     "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"
   }
 }