Spaces:
Sleeping
Sleeping
File size: 2,126 Bytes
30fc0eb 48f37f5 30fc0eb 48f37f5 30fc0eb 48f37f5 30fc0eb 48f37f5 30fc0eb 48f37f5 30fc0eb 48f37f5 30fc0eb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
# app_offline_ner_min.py
import os
os.environ["TRANSFORMERS_OFFLINE"] = "1" # force offline per HF docs
os.environ["TOKENIZERS_PARALLELISM"] = "false"
import torch
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
import gradio as gr
# point to your local snapshot downloaded by prepare_model.py
# path: ./models/biomedical-ner-all
HERE = os.path.dirname(os.path.abspath(__file__))
LOCAL_MODEL_DIR = os.path.join(HERE, "models", "biomedical-ner-all")
# load strictly from disk
tokenizer = AutoTokenizer.from_pretrained(LOCAL_MODEL_DIR, local_files_only=True)
model = AutoModelForTokenClassification.from_pretrained(LOCAL_MODEL_DIR, local_files_only=True)
device = 0 if torch.cuda.is_available() else -1
ner_pipe = pipeline(
task="token-classification", # NER
model=model,
tokenizer=tokenizer,
aggregation_strategy="simple", # merge subword tokens into entities
device=device
)
def run_ner(text: str):
if not text.strip():
return {"text": "", "entities": []}, []
out = ner_pipe(text)
highlighted = {
"text": text,
"entities": [
{
"entity": r["entity_group"],
"start": int(r["start"]),
"end": int(r["end"]),
"score": float(r["score"]),
}
for r in out
],
}
# list-of-lists in a fixed column order
rows = [
[r["entity_group"], r["word"], float(r["score"]), int(r["start"]), int(r["end"])]
for r in out
]
return highlighted, rows
with gr.Blocks() as demo:
gr.Markdown("# 🩺 Biomedical NER (offline, local model)")
inp = gr.Textbox(label="Enter text", value="Patient has a history of asthma treated with albuterol.")
ner_view = gr.HighlightedText(label="Entities", combine_adjacent=True)
table = gr.Dataframe(
label="Raw predictions",
headers=["entity", "word", "score", "start", "end"], # <-- headers for list-of-lists
interactive=False,
)
inp.change(run_ner, inp, [ner_view, table])
demo.launch(debug=True)
|