Spaces:
Runtime error
Runtime error
File size: 1,467 Bytes
62b4925 b4ebfe1 62b4925 3befb29 593a7a9 62b4925 4bad7b8 62b4925 11710d1 |
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 |
import json
from json import JSONDecodeError
import streamlit as st
from datasets import Dataset
from spacy_to_hf import spacy_to_hf
demo_option = [
{
"text": "Planned to go to the Apple Storefront on Tuesday",
"spans": [
{"start": 0, "end": 7, "label": "Action"},
{"start": 21, "end": 37, "label": "Loc"},
{"start": 41, "end": 48, "label": "Date"},
],
}
]
tokenizers = [
"bert-base-uncased",
"bert-base-cased",
"distilbert-base-uncased",
"distilbert-base-cased",
"roberta-base",
]
st.title("Spacy to HuggingFace converter")
st.markdown("[Homepage](https://github.com/ben-epstein/spacy-to-hf)")
tok = st.selectbox("Pick a tokenizer", tokenizers)
spacy_data = st.text_area("Input your NER Span data here")
if spacy_data or st.button("Or try an example"):
run_data = None
if spacy_data:
try:
run_data = json.loads(spacy_data)
except JSONDecodeError as e:
st.warning(f"Invalid JSON data, try again\n{str(e)}")
else:
run_data = demo_option
if run_data:
st.write("Spacy input data:")
st.json(run_data)
try:
hf_data = spacy_to_hf(run_data, tok)
df = Dataset.from_dict(hf_data).to_pandas()
st.write("Output huggingface format:")
st.dataframe(df)
except Exception as e:
st.error(f"Failed to create tokens and tags: {str(e)}")
|