import requests API_URL = "https://api-inference.huggingface.co/models/jkang/espnet2_librispeech_100_conformer_word" headers = {"Authorization": f"Bearer {API_TOKEN}"} def query(filename): with open(filename, "rb") as f: data = f.read() response = requests.post(API_URL, headers=headers, data=data) return response.json() output = query("sample1.flac")

handler.py

@@ -1,34 +1,12 @@
-from typing import  Dict, List, Any
-from optimum.onnxruntime import ORTModelForSequenceClassification
-from transformers import pipeline, AutoTokenizer
+import requests
 
+API_URL = "https://api-inference.huggingface.co/models/jkang/espnet2_librispeech_100_conformer_word"
+headers = {"Authorization": f"Bearer {API_TOKEN}"}
 
-class EndpointHandler():
-    def __init__(self, path=""):
-        # load the optimized model
-        model = ORTModelForSequenceClassification.from_pretrained(path)
-        tokenizer = AutoTokenizer.from_pretrained(path)
-        # create inference pipeline
-        self.pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)
+def query(filename):
+    with open(filename, "rb") as f:
+        data = f.read()
+    response = requests.post(API_URL, headers=headers, data=data)
+    return response.json()
 
-
-    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.
-        """
-        inputs = data.pop("inputs", data)
-        parameters = data.pop("parameters", None)
-
-        # pass inputs with all kwargs in data
-        if parameters is not None:
-            prediction = self.pipeline(inputs, **parameters)
-        else:
-            prediction = self.pipeline(inputs)
-        # postprocess the prediction
-        return prediction
+output = query("sample1.flac")