Add application file

app.py

@@ -0,0 +1,57 @@
+import spacy
+from spacy import displacy
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+import gradio as gr
+import torch
+import difflib
+import nltk
+nltk.download("punkt")
+from nltk.tokenize import sent_tokenize
+
+
+nlp = spacy.load("en_test_L1_model")
+model = T5ForConditionalGeneration.from_pretrained("Unbabel/gec-t5_small")
+tokenizer = T5Tokenizer.from_pretrained('t5-small')
+
+
+def text_analysis(text):
+    sentences = sent_tokenize(text)
+    processed_sentences = []
+    highlighted_sentences = []
+    for sentence in sentences:
+        doc = nlp(sentence)
+        html_highlight = displacy.render(doc, style="span", options = {"compact": True})
+        html_highlight = (
+            "<div style='max-width:100%; max-height:360px; overflow:auto'>"
+            + html_highlight
+            + "</div>"
+        )
+        processed_sentences.append(html_highlight)
+        inputs = tokenizer("gec: " + sentence, return_tensors="pt")
+        with torch.no_grad():
+            outputs = model.generate(**inputs, max_length=128, num_beams=4, early_stopping=True)
+        corrected_sentence = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        diff = difflib.ndiff(sentence.split(), corrected_sentence.split())
+        highlighted_output = ""
+        for word in diff:
+            if word.startswith("+ "):
+                highlighted_output += f"<span style='color: green; font-weight: bold;'>{word[2:]}</span> "
+            elif word.startswith("- "):
+                highlighted_output += f"<span style='color: red; text-decoration: line-through;'>{word[2:]}</span> "
+            else:
+                highlighted_output += word[2:] + " "
+        highlighted_sentences.append(f"<p><b>Corrected:</b> {highlighted_output}</p>")
+    return "<hr>".join(processed_sentences) + "<hr>", "<hr>".join(highlighted_sentences)
+        
+
+demo = gr.Interface(
+    text_analysis,
+    gr.Textbox(placeholder="Enter sentence here..."),
+    ["html", "html"],
+    examples=[
+        ["Then there was a sharp decrease so by 2013 the worldwide outlay accounted for 214 billions. Moreother there is a huge difference between part of 60+ years people. It is clearly seen that in Yemen the share of children before 14 years tend to become less - from 50,1% in 2000 to 37% in 2050."],
+        ["In post - school 70 percent were the same men a postgraduate diploma and women undergraduate diploma. Parents can try to know friends of their child, so they will know what they are doing and who they are."],
+    ],
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,174 @@
+aiofiles==23.2.1
+altair==5.4.1
+anyio==4.6.2.post1
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asttokens==2.4.1
+async-lru==2.0.4
+attrs==24.2.0
+babel==2.16.0
+beautifulsoup4==4.12.3
+bleach==6.2.0
+blis==0.7.11
+catalogue==2.0.10
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.4.0
+click==8.1.7
+comm==0.2.2
+confection==0.1.5
+contourpy==1.3.0
+cycler==0.12.1
+cymem==2.0.8
+debugpy==1.8.7
+decorator==5.1.1
+defusedxml==0.7.1
+en_test_L1_model @ https://huggingface.co/Zlovoblachko/en_test_L1_model/resolve/main/en_test_L1_model-any-py3-none-any.whl
+exceptiongroup==1.2.2
+executing==2.1.0
+fastapi==0.115.4
+fastjsonschema==2.20.0
+ffmpy==0.4.0
+filelock==3.16.1
+fonttools==4.54.1
+fqdn==1.5.1
+fsspec==2024.10.0
+gradio==3.41.0
+gradio_client==0.5.0
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.26.2
+idna==3.10
+importlib_resources==6.4.5
+ipykernel==6.29.5
+ipython==8.29.0
+ipywidgets==8.1.5
+isoduration==20.11.0
+jedi==0.19.1
+Jinja2==3.1.4
+joblib==1.4.2
+json5==0.9.25
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter==1.1.1
+jupyter-console==6.6.3
+jupyter-events==0.10.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyter_server==2.14.2
+jupyter_server_terminals==0.5.3
+jupyterlab==4.2.5
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.13
+kiwisolver==1.4.7
+langcodes==3.4.1
+language_data==1.2.0
+marisa-trie==1.2.1
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+matplotlib-inline==0.1.7
+mistune==3.0.2
+mpmath==1.3.0
+murmurhash==1.0.10
+narwhals==1.13.1
+nbclient==0.10.0
+nbconvert==7.16.4
+nbformat==5.10.4
+nest-asyncio==1.6.0
+networkx==3.4.2
+nltk==3.9.1
+notebook==7.2.2
+notebook_shim==0.2.4
+numpy==1.26.4
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
+orjson==3.10.11
+overrides==7.7.0
+packaging==24.1
+pandas==2.2.3
+pandocfilters==1.5.1
+parso==0.8.4
+pathlib_abc==0.1.1
+pathy==0.11.0
+pexpect==4.9.0
+pillow==10.4.0
+platformdirs==4.3.6
+preshed==3.0.9
+prometheus_client==0.21.0
+prompt_toolkit==3.0.48
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pycparser==2.22
+pydantic==1.10.18
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.2.0
+python-dateutil==2.9.0.post0
+python-json-logger==2.0.7
+python-multipart==0.0.17
+pytz==2024.2
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rpds-py==0.20.1
+semantic-version==2.10.0
+Send2Trash==1.8.3
+sentencepiece==0.2.0
+six==1.16.0
+smart-open==6.4.0
+sniffio==1.3.1
+soupsieve==2.6
+spacy==3.4.4
+spacy-alignments==0.9.1
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+spacy-transformers==1.2.1
+srsly==2.4.8
+stack-data==0.6.3
+starlette==0.41.2
+sympy==1.13.1
+terminado==0.18.1
+thinc==8.1.12
+tinycss2==1.4.0
+tokenizers==0.13.3
+tomli==2.0.2
+torch==2.5.1
+tornado==6.4.1
+tqdm==4.66.6
+traitlets==5.14.3
+transformers==4.26.1
+triton==3.1.0
+typer==0.7.0
+types-python-dateutil==2.9.0.20241003
+typing_extensions==4.12.2
+tzdata==2024.2
+uri-template==1.3.0
+urllib3==2.2.3
+uvicorn==0.32.0
+wasabi==0.10.1
+wcwidth==0.2.13
+webcolors==24.8.0
+webencodings==0.5.1
+websocket-client==1.8.0
+websockets==11.0.3
+widgetsnbextension==4.0.13