File size: 1,904 Bytes
dc2b383 db3682f c746e15 154ad0d d521794 0997b05 a6ee429 b3d4005 69d224b 0a1cb7b b3d4005 a6ee429 69d224b b3d4005 a6ee429 b3d4005 a6ee429 b3d4005 dc2b383 d521794 b3d4005 a6ee429 dc2b383 26d45f0 a6ee429 dc2b383 a6ee429 90328f3 a6ee429 0997b05 d521794 b3d4005 |
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 52 53 54 55 56 57 58 59 60 61 62 63 64 |
from transformers import Pipeline
from transformers.pipelines import PIPELINE_REGISTRY
import floret
from huggingface_hub import hf_hub_download
class Pipeline_One(Pipeline):
# def __init__(self, model_path: str):
# """
# Initialize the Floret language detection pipeline
# Args:
# model_path (str): Path to the .bin model file
# """
# super().__init__()
# self.model = floret.FastText.load_model(model_path)
# def __init__(self, model_name="floret_model.bin", repo_id="Maslionok/pipeline1", revision="main", **kwargs):
# """
# Initialize the Floret language detection pipeline.
# Args:
# model_name (str): The name of the Floret model file.
# repo_id (str): The Hugging Face repository ID.
# revision (str): The branch/revision to download from.
# """
# super().__init__(**kwargs)
# model_path = hf_hub_download(repo_id=repo_id, filename=model_name, revision=revision)
# self.model = floret.load_model(model_path)
# def _sanitize_parameters(self, **kwargs):
# # Add any additional parameter handling if necessary
# return {}, {}, {}
def _sanitize_parameters(self, **kwargs):
preprocess_kwargs = {}
if "text" in kwargs:
preprocess_kwargs["text"] = kwargs["text"]
return preprocess_kwargs, {}, {}
def preprocess(self, text, **kwargs):
print("this is preprocessing:")
print(text)
return text
def _forward(self, inputs):
model_output = self.model.predict(**inputs, k=1)
return model_output
def postprocess(self, outputs, **kwargs):
return outputs
# PIPELINE_REGISTRY.register_pipeline(
# task="language-detection",
# pipeline_class=Pipeline_One,
# default={"model": None},
# ) |