Create handler.py

handler.py

@@ -0,0 +1,28 @@
+from transformers import pipeline, M2M100ForConditionalGeneration, M2M100Tokenizer,QuantoConfig
+from typing import Dict, List, Any
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        # load the optimized model
+        model = M2M100ForConditionalGeneration.from_pretrained(path)
+        tokenizer = M2M100Tokenizer.from_pretrained(path)
+        # create inference pipeline
+        self.pipeline = pipeline("translation", model=model, tokenizer=tokenizer)
+
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        """
+        Args:
+            data (:obj:):
+                includes the input data and the parameters for the inference.
+        Return:
+            A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing :
+                - "label": A string representing what the label/class is. There can be multiple labels.
+                - "score": A score between 0 and 1 describing how confident the model is for this label/class.
+        """
+        text = data.get("text", data)
+        lang = data.get("langId",data)
+        encoded = tokenizer(text, return_tensors="pt")
+        generated_tokens = model.generate(**encoded, forced_bos_token_id=tokenizer.get_lang_id(lang))
+        result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
+        return {'transdlated':result}