utils.py

from huggingface_hub import login
import json
import evaluate
import os

def hf_login():
    hf_token = os.getenv("HF_Token")
    print(hf_token)
    if hf_token is None:
        with open("credentials.json", "r") as f:
            hf_token = json.load(f)["token"]
    login(token=hf_token, add_to_git_credential=True)

def data(dataset):
    for i, item in enumerate(dataset):
        yield {**item["audio"], "reference": item["norm_text"]}

def compute_wer(references, predictions):
    wer_metric = evaluate.load("wer")
    wer = wer_metric.compute(references=references, predictions=predictions)
    wer = round(100 * wer, 2)
    return wer


# def run_tests (dataset_choice:str, model:str):

#     MoDeL = Model()
#     MoDeL.select(model)
#     MoDeL.load()
#     DaTaSeT = Dataset(100)
#     DaTaSeT.load(dataset_choice)
#     references, predictions = MoDeL.process(DaTaSeT)
#     wer = compute_wer(references=references, predictions=predictions)
#     return wer