intermediate commit

app.py

@@ -113,7 +113,11 @@ def main():
         saveFileCheckbox.change(gh.updateTextbox, inputs=saveFileCheckbox, outputs=filename)
         saveFileCheckbox.change(gh.updateTextbox, inputs=saveFileCheckbox, outputs=filenamePdf)
 
-        recognizeBtn.click(gh.handleRecognizeBtn, outputs=[recognizedText], inputs=[audioFiles, fastWhisperModel, device, compute_type, beamSize, vadFilter, minSilenceDurationMs, speechPadMs, temp0, temp1, temp2, wordTimestamps, noSpeechThreshold, conditionOnPreviousText, gr.State(GLUED_AUDIO_FILENAME), gr.State(OUTPUT_PATH)])
+        recognizeBtn.click(
+            gh.handleRecognizeBtn, 
+            inputs=[audioFiles, fastWhisperModel, device, compute_type, beamSize, vadFilter, minSilenceDurationMs, speechPadMs, temp0, temp1, temp2, wordTimestamps, noSpeechThreshold, conditionOnPreviousText, gr.State(GLUED_AUDIO_FILENAME), gr.State(OUTPUT_PATH)]
+            outputs=[recognizedText], 
+            )
         
         # Если пайплайн включен то тогда делаем автоматически
         # автоматический пайплайн

handlers/glueAudio.py

@@ -1,11 +1,17 @@
 from pydub import AudioSegment
 
 class GlueAudio():
-    def glue(self, audioFiles):
+    def glue(self, audio_files: list, output_path: str, output_filename: str) -> Path:
-        glued = AudioSegment.empty()
+        """
+        Склеивает аудиофайлы с помощью FFmpeg, используя промежуточный список файлов.
+        Этот метод чрезвычайно эффективен по памяти и скорости.
 
-        for audioFile in audioFiles:
+        Args:
-            audio = AudioSegment.from_file(audioFile)
+            audio_files (list): Список путей к исходным аудиофайлам.
-            glued += audio
+            output_path (str): Директория для сохранения итогового файла.
+            output_filename (str): Имя итогового склеенного файла.
+
+        Returns:
+            Path: Путь к созданному склеенному файлу.
+        """
 
-        return glued

handlers/gradioHandler.py

@@ -9,14 +9,25 @@ class GradioHandlers:
         self.ga = GlueAudio()
         self.ConvertMdToPdf = ConvertMdToPdf()
         self.FasterWhisper = FasterWhisper()
-        self.llm_factory = llm_factory # Сохраняем фабрику
+        self.llm_factory = llm_factory
 
-    def handleRecognizeBtn(self, audioFiles, model, device, compute_type, beamSize, vadFilter, minSilenceDurationMs, speechPadMs, temp0, temp1, temp2, wordTimestamps, noSpeechThreshold, conditionOnPreviousText, filename, outPath):
+    def handleRecognizeBtn(
-        audioFile = self.ga.glue(audioFiles)
+                            self, 
+                            audioFiles, model, device, compute_type, beamSize, vadFilter, 
+                            minSilenceDurationMs, speechPadMs, temp0, temp1, temp2, wordTimestamps, 
+                            noSpeechThreshold, conditionOnPreviousText, filename, outPath
+                            ):
+        try:
+            audioFile = self.ga.glue(audioFiles, output)
             file = self.fh.saveFile(filename, audioFile, outPath)
 
             return self.FasterWhisper.recognize(model, device, compute_type, file, beamSize, vadFilter, minSilenceDurationMs, speechPadMs, temp0, temp1, temp2, wordTimestamps, noSpeechThreshold, conditionOnPreviousText)
         
+        except (FileNotFoundError, RuntimeError) as e:
+            # Если FFmpeg не найден или произошла ошибка, сообщаем пользователю
+            gr.Warning(str(e))
+            return "" # Возвращаем пустую строку в текстовое поле
+
     # Функция улучшения текста
     def generateByCondition(self, api_key, llm_provider, llm_model, system_prompt, recognized_text, llm_temperature, is_pipeline_enabled, trigger, isSaveFile, filename, filenamePdf, output_path):
         try:

requirements.txt

@@ -100,3 +100,118 @@ uvicorn==0.35.0
 webencodings==0.5.1
 websockets==15.0.1
 zopfli==0.2.3.post1
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.13.0
+aiosignal==1.4.0
+annotated-types==0.7.0
+anyio==4.10.0
+attrs==25.4.0
+audioop-lts==0.2.2
+av==15.1.0
+beautifulsoup4==4.13.5
+Brotli==1.1.0
+bs4==0.0.2
+certifi==2025.8.3
+cffi==2.0.0
+charset-normalizer==3.4.3
+click==8.2.1
+coloredlogs==15.0.1
+colour==0.1.5
+cssselect2==0.8.0
+ctranslate2==4.6.0
+distro==1.9.0
+dotenv==0.9.9
+exceptiongroup==1.3.0
+fastapi==0.116.1
+faster-whisper==1.2.0
+ffmpeg-python==0.2.0
+ffmpy==0.6.1
+filelock==3.19.1
+flatbuffers==25.2.10
+flatlatex==0.15
+fonttools==4.59.2
+frozenlist==1.8.0
+fsspec==2025.9.0
+future==1.0.0
+g4f==0.6.3.5
+gradio==5.44.1
+gradio_client==1.12.1
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.1.9
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.34.4
+humanfriendly==10.0
+idna==3.10
+iso639-lang==2.6.3
+Jinja2==3.1.6
+jiter==0.10.0
+joblib==1.5.2
+langdetect==1.0.9
+littleutils==0.2.4
+markdown-it-py==3.0.0
+markdown_pdf==1.9
+MarkupSafe==3.0.2
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.7.0
+nest-asyncio==1.6.0
+nltk==3.9.1
+numpy==2.2.6
+onnxruntime==1.22.1
+openai==1.106.1
+orjson==3.11.3
+outdated==0.2.2
+packaging==25.0
+pandas==2.3.2
+pillow==11.3.0
+propcache==0.4.0
+protobuf==6.32.0
+pycparser==2.22
+pycryptodome==3.23.0
+pydantic==2.11.7
+pydantic_core==2.33.2
+pydub==0.25.1
+pydyf==0.11.0
+Pygments==2.19.2
+pylatexenc==2.10
+pymultidictionary==1.3.2
+PyMuPDF==1.26.4
+pyperclip==1.9.0
+pyphen==0.17.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.1
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+regex==2025.9.1
+requests==2.32.5
+rich==14.1.0
+ruff==0.12.12
+safehttpx==0.1.6
+semantic-version==2.10.0
+setuptools==80.9.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+soupsieve==2.8
+starlette==0.47.3
+sympy==1.14.0
+tinycss2==1.4.0
+tinyhtml5==2.0.0
+tkmacosx==1.0.5
+tokenizers==0.22.0
+tomlkit==0.13.3
+tqdm==4.67.1
+typer==0.17.4
+typing-inspection==0.4.1
+typing_extensions==4.15.0
+tzdata==2025.2
+urllib3==2.5.0
+uvicorn==0.35.0
+webencodings==0.5.1
+websockets==15.0.1
+yarl==1.22.0
+zopfli==0.2.3.post1

test.py

@@ -0,0 +1,19 @@
+from handlers.convertMdToPdf import ConvertMdToPdf
+import re
+# Создаем экземпляр класса
+converter = ConvertMdToPdf()
+
+# Тестовые примеры дробей
+test_cases = [
+    r"$\frac{1}{2}$",          # простая дробь
+    r"$\dfrac{3}{4}$",         # дробь с displaystyle
+    r"$\frac{a}{b} + \frac{c}{d}$",  # сложение дробей
+    r"$$\frac{x^2}{y^3}$$",    # блочная дробь
+    r"$\frac{\partial f}{\partial x}$"  # частная производная
+]
+
+for latex in test_cases:
+    result = converter.replace_math(re.search(r'\$\$(.*?)\$\$|\$(.*?)\$', latex))
+    print(f"Input: {latex}")
+    print(f"Output: {result}")
+    print("---")