Scan for secrets using finetuned xlm-RoBERTa-base model
(chunks, model=model, tokenizer=tokenizer)
| 168 | |
| 169 | |
| 170 | def get_secrets_BERT(chunks, model=model, tokenizer=tokenizer): |
| 171 | """Scan for secrets using finetuned xlm-RoBERTa-base model""" |
| 172 | bert_secret = [] |
| 173 | |
| 174 | |
| 175 | for chunk in chunks: |
| 176 | temp_secrets = classify_tokens(chunk, model, tokenizer, device=device) |
| 177 | if temp_secrets != [] and temp_secrets: |
| 178 | bert_secret.append({"secret":temp_secrets, 'chunk':chunk}) |
| 179 | |
| 180 | |
| 181 | return bert_secret |
| 182 | |
| 183 | async def scan_secret(doc): |
| 184 | """Main function to scan the document for secrets""" |
no test coverage detected