Merge branch 'English' of https://github.com/philpw99/VideoCaptioner …

…into English

Dockerfile

@@ -0,0 +1,43 @@
+FROM python:3.10-slim-bookworm
+
+WORKDIR /app
+
+# 配置apt镜像源
+RUN rm -rf /etc/apt/sources.list.d/* && \
+    rm -f /etc/apt/sources.list && \
+    echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian/ bookworm main contrib non-free non-free-firmware" > /etc/apt/sources.list && \
+    echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian/ bookworm-updates main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
+    echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian/ bookworm-backports main contrib non-free non-free-firmware" >> /etc/apt/sources.list && \
+    echo "deb https://mirrors.tuna.tsinghua.edu.cn/debian-security bookworm-security main contrib non-free non-free-firmware" >> /etc/apt/sources.list
+
+# 安装系统依赖
+RUN apt-get update && \
+    apt-get install -y \
+    curl \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# 先复制依赖文件并安装
+COPY streamlit_app/requirements.txt .
+RUN pip3 install --no-cache-dir -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+# 复制应用代码
+COPY . .
+
+# 设置环境变量
+ARG OPENAI_BASE_URL
+ARG OPENAI_API_KEY
+ENV OPENAI_BASE_URL=${OPENAI_BASE_URL:-https://dg.bkfeng.top/v1}
+ENV OPENAI_API_KEY=${OPENAI_API_KEY}
+
+# 创建临时目录并设置权限
+RUN mkdir -p temp && chmod 777 temp
+
+# 暴露端口
+EXPOSE 8501
+
+# 健康检查
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+# 启动应用
+ENTRYPOINT ["streamlit", "run", "streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]

app/core/bk_asr/ASRData.py

@@ -297,6 +297,34 @@ def to_ass(self, style_str: str = None, layout: str = "Original On Top", save_pa
                 f.write(ass_content)
         return ass_content
 
+    def to_vtt(self, save_path=None) -> str:
+        """转换为WebVTT字幕格式
+        
+        Args:
+            save_path: 可选的保存路径
+            
+        Returns:
+            str: WebVTT格式的字幕内容
+        """
+        # WebVTT头部
+        vtt_lines = ['WEBVTT\n']
+
+        for n, seg in enumerate(self.segments, 1):
+            # 转换时间戳格式从毫秒到 HH:MM:SS.mmm
+            start_time = seg._ms_to_srt_time(seg.start_time).replace(',', '.')
+            end_time = seg._ms_to_srt_time(seg.end_time).replace(',', '.')
+
+            # 添加序号（可选）和时间戳
+            vtt_lines.append(f"{n}\n{start_time} --> {end_time}\n{seg.transcript}\n")
+
+        vtt_text = "\n".join(vtt_lines)
+
+        if save_path:
+            with open(save_path, 'w', encoding='utf-8') as f:
+                f.write(vtt_text)
+
+        return vtt_text
+
     def merge_segments(self, start_index: int, end_index: int, merged_text: str = None):
             """合并从 start_index 到 end_index 的段（包含）。"""
             if start_index < 0 or end_index >= len(self.segments) or start_index > end_index:

app/core/bk_asr/BaseASR.py

@@ -65,7 +65,7 @@ def _set_data(self):
     def _get_key(self):
         return f"{self.__class__.__name__}-{self.crc32_hex}"
 
-    def run(self, callback=None, **kwargs):
+    def run(self, callback=None, **kwargs) -> ASRData:
         k = self._get_key()
         if k in self.cache and self.use_cache:
             resp_data = self.cache[k]

app/core/bk_asr/BcutASR.py

@@ -8,7 +8,6 @@
 from .ASRData import ASRDataSeg
 from .BaseASR import BaseASR
 from ..utils.logger import setup_logger
-from PyQt5.QtCore import QSettings
 
 logger = setup_logger("bcut_asr")
 
@@ -51,15 +50,6 @@ def __init__(self, audio_path: str | bytes, use_cache: bool = False, need_word_t
 
         self.need_word_time_stamp = need_word_time_stamp
 
-        self.settings = QSettings(QSettings.IniFormat, QSettings.UserScope,
-                                  'VideoCaptioner', 'VideoCaptioner')
-        current_date = time.strftime('%Y-%m-%d')
-        last_date = self.settings.value('bcutasr/last_date', '')
-        if current_date != last_date:
-            self.settings.setValue('bcutasr/last_date', current_date)
-            self.settings.setValue('bcutasr/daily_calls', 0)
-            self.settings.sync()  # 强制写入
-
     def upload(self) -> None:
         """申请上传"""
         if not self.file_binary:
@@ -152,13 +142,6 @@ def _run(self, callback=None, **kwargs):
         if callback is None:
             callback = lambda x, y: None
 
-        daily_calls = int(self.settings.value('bcutasr/daily_calls', 0))
-        if daily_calls >= self.MAX_DAILY_CALLS:
-            raise Exception(f"请明天再试")
-        self.settings.setValue('bcutasr/daily_calls', daily_calls + 1)
-        self.settings.sync()  # 强制写入
-        print(self.settings.value('bcutasr/daily_calls', 0))
-
         callback(0, "上传中")
         self.upload()
 

app/core/thread/transcript_thread.py

@@ -209,8 +209,5 @@ def progress_callback(self, value, message):
 
     # Is the current config is using FasterWhipser and translate to English?
     def isFasterWhisperTranslate(self):
-        if cfg.transcribe_model.value == TranscribeModelEnum.FASTER_WHISPER and cfg.faster_whisper_translate_to_english.value:
-            return True
-        else:
-            return False
+        return cfg.transcribe_model.value == TranscribeModelEnum.FASTER_WHISPER and cfg.faster_whisper_translate_to_english.value