How to use Common Voice 11 with 🤗Datasets

how_to_use_cv11.py

# Load the dataset (locally)

from datasets import load_dataset

cv_11 = load_dataset("mozilla-foundation/common_voice_11_0", "hi", split="train")

# Stream the dataset

from datasets import load_dataset

cv_11 = load_dataset("mozilla-foundation/common_voice_11_0", "hi", split="train", streaming=True)

print(next(iter(cv_11)))

# Create a PyTorch dataloader

from datasets import load_dataset
from torch.utils.data.sampler import BatchSampler, RandomSampler

cv_11 = load_dataset("mozilla-foundation/common_voice_11_0", "hi", split="train")
batch_sampler = BatchSampler(RandomSampler(cv_11), batch_size=32, drop_last=False)
dataloader = DataLoader(cv_11, batch_sampler=batch_sampler)

# Create a streaming PyTorch dataloader

from datasets import load_dataset
from torch.utils.data import DataLoader

cv_11 = load_dataset("mozilla-foundation/common_voice_11_0", "hi", split="train")
dataloader = DataLoader(cv_11, batch_size=32)