feat: Initial commit, add sentiment app

.gitignore

@@ -0,0 +1 @@
+.venv/

app.py

@@ -0,0 +1,58 @@
+"""Gradio app that showcases Scandinavian zero-shot text classification models."""
+
+import gradio as gr
+from transformers import pipeline
+from luga import language as detect_language
+
+
+# Load the zero-shot classification pipeline
+classifier = pipeline(
+    "zero-shot-classification", model="alexandrainst/scandi-nli-large"
+)
+
+
+def sentiment_classification(doc: str) -> str:
+    """Classify text into sentiment categories.
+
+    Args:
+        doc (str):
+            Text to classify.
+
+    Returns:
+        str:
+            The predicted sentiment category.
+    """
+    # Detect the language of the text
+    language = detect_language(doc).name
+
+    # Get hypothesis template and candidate labels depending on the language
+    if language == "da":
+        hypothesis_template = "Dette eksempel er {}."
+        candidate_labels = ["positivt", "negativt", "neutralt"]
+    elif language == "sv":
+        hypothesis_template = "Detta exempel är {}."
+        candidate_labels = ["positivt", "negativt", "neutralt"]
+    elif language == "no":
+        hypothesis_template = "Dette eksemplet er {}."
+        candidate_labels = ["positivt", "negativt", "nøytralt"]
+
+    # Run the classifier on the text
+    result = classifier(
+        doc, candidate_labels=candidate_labels, hypothesis_template=hypothesis_template
+    )
+
+    # Return the predicted label
+    return result["labels"][0]
+
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=sentiment_classification,
+    inputs=gr.inputs.Textbox(lines=5, label="Text"),
+    outputs=gr.outputs.Label(type="text"),
+    title="Scandinavian Zero-Shot Text Classification",
+    description="Classify text into sentiment categories.",
+)
+
+# Run the app
+interface.launch()

requirements.txt

@@ -0,0 +1,66 @@
+aiohttp==3.8.3
+aiosignal==1.3.1
+anyio==3.6.2
+async-timeout==4.0.2
+attrs==22.1.0
+bcrypt==4.0.1
+certifi==2022.9.24
+cffi==1.15.1
+charset-normalizer==2.1.1
+click==8.1.3
+contourpy==1.0.6
+cryptography==38.0.4
+cycler==0.11.0
+fastapi==0.88.0
+ffmpy==0.3.0
+filelock==3.8.0
+fonttools==4.38.0
+frozenlist==1.3.3
+fsspec==2022.11.0
+gradio==3.12.0
+h11==0.12.0
+httpcore==0.15.0
+httpx==0.23.1
+huggingface-hub==0.11.1
+idna==3.4
+Jinja2==3.1.2
+kiwisolver==1.4.4
+linkify-it-py==1.0.3
+markdown-it-py==2.1.0
+MarkupSafe==2.1.1
+matplotlib==3.6.2
+mdit-py-plugins==0.3.1
+mdurl==0.1.2
+multidict==6.0.2
+numpy==1.23.5
+orjson==3.8.2
+packaging==21.3
+pandas==1.5.2
+paramiko==2.12.0
+Pillow==9.3.0
+pycparser==2.21
+pycryptodome==3.16.0
+pydantic==1.10.2
+pydub==0.25.1
+PyNaCl==1.5.0
+pyparsing==3.0.9
+python-dateutil==2.8.2
+python-multipart==0.0.5
+pytz==2022.6
+PyYAML==6.0
+regex==2022.10.31
+requests==2.28.1
+rfc3986==1.5.0
+six==1.16.0
+sniffio==1.3.0
+starlette==0.22.0
+tokenizers==0.13.2
+torch==1.12.1
+tqdm==4.64.1
+transformers==4.24.0
+typing_extensions==4.4.0
+uc-micro-py==1.0.1
+urllib3==1.26.13
+uvicorn==0.20.0
+websockets==10.4
+yarl==1.8.1