datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
ViSpeech-Gender-Dialect-Classificationimport datasets as hugDS
import pandas as pd
import os
os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
from df.io import resample
from df.enhance import enhance, init_df
import torch
import warnings
df_model, df_state, _ = init_df()
SAMPLING_RATE = 16_000
def normalize_vietmed(example):
global vietmed_info
example["gender"] = vietmed_info[vietmed_info["Speaker ID"] == example["Speaker ID"]]["Gender"].values[0].lower()
example["dialect"] = vietmed_info[vietmed_info["Speaker ID"] ==… See the full description on the dataset page: https://huggingface.co/datasets/hr16/ViSpeech-Gender-Dialect-Classification.Gender_Classificationnptel_en_with_gender_and_speaker_classificationnptel_en_dataset_gender_speaker_classificationgender-classification-ASR-Human-Eval