init

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Swedish Dependency Parser
+emoji: 🌲
+colorFrom: green
+colorTo: blue
+sdk: gradio
+sdk_version: 5.31.0
+app_file: app.py
+pinned: false
+---
+
+Swedish dependency parsing using a fine-tuned BERT model. Analyzes grammatical relationships between words in Swedish sentences using Universal Dependencies.
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,80 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+import numpy as np
+
+MODEL = "elliot-evno/kb-bert-swedish-dep" 
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+model = AutoModelForTokenClassification.from_pretrained(MODEL)
+
+DEP_LABELS = ["_", "acl", "acl:cleft", "acl:relcl", "advcl", "advmod", "amod", "appos", "aux", "aux:pass", "case", "cc", "ccomp", "compound:prt", "conj", "cop", "csubj", "csubj:pass", "det", "discourse", "dislocated", "expl", "fixed", "flat:name", "iobj", "mark", "nmod", "nmod:poss", "nsubj", "nsubj:outer", "nsubj:pass", "nummod", "obj", "obl", "obl:agent", "orphan", "parataxis", "punct", "root", "vocative", "xcomp"]
+
+def predict_dependencies(text):
+    """Predict dependency relations for input text"""
+    if not text.strip():
+        return "Please enter some Swedish text!"
+    
+    tokens = text.split()  
+    inputs = tokenizer(tokens, is_split_into_words=True, return_tensors="pt", 
+                      truncation=True, padding=True)
+    
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        predicted_label_ids = predictions.argmax(-1)
+    
+    word_ids = inputs.word_ids()
+    predicted_labels = []
+    
+    for i, token in enumerate(tokens):
+        # Find the first subtoken for this word
+        word_predictions = []
+        for j, word_id in enumerate(word_ids):
+            if word_id == i:
+                word_predictions.append(predicted_label_ids[0][j].item())
+        
+        if word_predictions:
+            # Use the prediction from the first subtoken
+            label_id = word_predictions[0]
+            if label_id < len(DEP_LABELS):
+                predicted_labels.append(DEP_LABELS[label_id])
+            else:
+                predicted_labels.append("UNK")
+        else:
+            predicted_labels.append("UNK")
+    
+    # Format output
+    result = []
+    for token, label in zip(tokens, predicted_labels):
+        result.append(f"{token} → {label}")
+    
+    return "\n".join(result)
+
+# Example Swedish sentences
+examples = [
+    "Jag heter Elliot.",
+    "När barnen kom hem från skolan åt de pizza med sina föräldrar.",
+    "Den svenska flickan som jag träffade igår läser en bok.",
+    "Stockholm är Sveriges huvudstad och en vacker stad."
+]
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=predict_dependencies,
+    inputs=gr.Textbox(
+        label="Swedish Text", 
+        placeholder="Enter Swedish text here...",
+        lines=3
+    ),
+    outputs=gr.Textbox(
+        label="Dependency Relations", 
+        lines=10
+    ),
+    title="🌲 Swedish Dependency Parser",
+    description="Enter Swedish text to get dependency relations using a fine-tuned BERT model. Shows grammatical relationships between words using Universal Dependencies format.",
+    examples=examples,
+    theme=gr.themes.Soft()
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers
+torch