Fixed some bugs, added dockerfile

Dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+COPY fast_align_config ./fast_align_config
+COPY src ./src
+COPY okapi-apps_gtk2-linux-x86_64_1.47.0 ./okapi-apps_gtk2-linux-x86_64_1.47.0
+COPY gradio_app.py .
+COPY requirements.txt .
+
+COPY fast_align .
+COPY atools .
+
+RUN pip install --no-cache-dir -r requirements.txt
+RUN python -m spacy download xx_ent_wiki_sm
+
+RUN apt-get update && \
+    apt-get install libgomp1 && \
+    apt-get install -y openjdk-17-jre-headless
+
+CMD ["python", "gradio_app.py"]
+
+# sudo docker build -t document-translator .
+# docker run -p 7860:7860 --rm -it document-translator

gradio_app.py

@@ -33,8 +33,7 @@ with gr.Blocks() as demo:
         gr.Interface(fn=translator.translate, inputs=["text", "text", "text"], outputs="text")
     with gr.Tab("Documents"):
         with gr.Row():
-            dropdown1 = gr.Dropdown(label="Source language", choices=["en", "ca"], value=None,
-                                    interactive=True)
+            dropdown1 = gr.Dropdown(label="Source language", choices=["en", "ca"], value=None, interactive=True)
             dropdown2 = gr.Dropdown(label="Target language", choices=["en", "ca"], value=None, interactive=True)
         gr.Markdown("First upload a file and and then you'll be able download it (but only once!)")
         with gr.Row():
@@ -44,4 +43,4 @@ with gr.Blocks() as demo:
         u.upload(fn=before_processing, inputs=None, outputs=[u, d]).then(upload_file, [u, dropdown1, dropdown2], [u, d])
         d.click(download_file, None, [u, d])
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(server_name="0.0.0.0", server_port=7860)

readme.md

@@ -24,4 +24,9 @@ need to use fastalign on that side since the current project already runs it.
 
 ### salamandrata7b_translator
 
-Class that uses huggingface's demo.
+Class that uses huggingface's demo.
+
+## Docker
+
+sudo docker build -t document-translator .
+docker run -p 7860:7860 --rm -it document-translator

src/translate_any_doc.py

@@ -368,6 +368,8 @@ def translate_document(input_file: str, source_lang: str, target_lang: str,
                        temp_folder: str = "tmp",
                        tikal_folder: str = "okapi-apps_gtk2-linux-x86_64_1.47.0", with_format: bool = True) -> str:
     input_filename = input_file.split("/")[-1]
+    os.makedirs(temp_folder, exist_ok=True)
+
     # copy the original file to the temporal folder to avoid common issues with tikal
     temp_input_file = os.path.join(temp_folder, input_filename)
     shutil.copy(input_file, temp_input_file)