Duplicate from ai4bharat/IndicNER

Co-authored-by: Umashankar <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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: IndicNER
+emoji: 📊
+colorFrom: indigo
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.15.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: ai4bharat/IndicNER
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+tokenizer = AutoTokenizer.from_pretrained("ai4bharat/IndicNER")
+
+model = AutoModelForTokenClassification.from_pretrained("ai4bharat/IndicNER")
+
+
+def get_ner(sentence):
+    tok_sentence = tokenizer(sentence, return_tensors='pt')
+
+    with torch.no_grad():
+        logits = model(**tok_sentence).logits.argmax(-1)
+        predicted_tokens_classes = [
+            model.config.id2label[t.item()] for t in logits[0]]
+
+        predicted_labels = []
+
+        previous_token_id = 0
+        word_ids = tok_sentence.word_ids()
+        for word_index in range(len(word_ids)):
+            if word_ids[word_index] == None:
+                previous_token_id = word_ids[word_index]
+            elif word_ids[word_index] == previous_token_id:
+                previous_token_id = word_ids[word_index]
+            else:
+                predicted_labels.append(predicted_tokens_classes[word_index])
+                previous_token_id = word_ids[word_index]
+
+        ner_output = []
+        for index in range(len(sentence.split(' '))):
+            ner_output.append(
+                (sentence.split(' ')[index], predicted_labels[index]))
+        return ner_output
+
+
+iface = gr.Interface(get_ner,
+                     gr.Textbox(placeholder="Enter sentence here..."),
+                     ["highlight"], description='The 11 languages covered by IndicNER are: Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, Telugu.',
+                     examples=['लगातार हमलावर हो रहे शिवपाल और राजभर को सपा की दो टूक, चिट्ठी जारी कर कहा- जहां जाना चाहें जा सकते हैं', 'ಶರಣ್ ರ ನೀವು ನೋಡಲೇಬೇಕಾದ ಟಾಪ್ 5 ಕಾಮಿಡಿ ಚಲನಚಿತ್ರಗಳು'], title='IndicNER',
+                     article='IndicNER is a model trained to complete the task of identifying named entities from sentences in Indian languages. Our model is specifically fine-tuned to the 11 Indian languages mentioned above over millions of sentences. The model is then benchmarked over a human annotated testset and multiple other publicly available Indian NER datasets.'
+                     )
+
+iface.launch(enable_queue=True)

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+torch
+sentencepiece==0.1.95
+datasets
+seqeval