Create handler.py
Browse files- handler.py +17 -0
handler.py
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import AutoTokenizer
|
| 2 |
+
|
| 3 |
+
class EndpointHandler():
|
| 4 |
+
def __init__(self, path=""):
|
| 5 |
+
self.tokenizer = AutoTokenizer.from_pretrained("otmanheddouch/shakespear-tokenizer")
|
| 6 |
+
|
| 7 |
+
def __call__(self, data: str] -> Dict[str, Any]]:
|
| 8 |
+
"""
|
| 9 |
+
data args:
|
| 10 |
+
data: text input
|
| 11 |
+
Return:
|
| 12 |
+
output (dict) : outputs with tokens and their ids
|
| 13 |
+
"""
|
| 14 |
+
tokens = self.tokenizer.tokenize()
|
| 15 |
+
tokens_ids = self.tokenizer.encode(example)
|
| 16 |
+
|
| 17 |
+
return {"tokens:"tokens, "ids":tokens_ids}
|