amanuelbyte/african_speech_dataset

---
dataset_info:
- config_name: amh
features:
- name: text
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
- name: audio
dtype:
audio:
decode: false
splits:
- name: train
num_bytes: 37922390
num_examples: 1045
download_size: 37692218
dataset_size: 37922390
- config_name: amharic
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: text
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 11686723853
num_examples: 32901
download_size: 11067717597
dataset_size: 11686723853
- config_name: hau
features:
- name: text
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
- name: audio
dtype:
audio:
decode: false
splits:
- name: train
num_bytes: 91812182
num_examples: 3496
download_size: 91066923
dataset_size: 91812182
- config_name: hausa
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: text
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 602620189
num_examples: 1572
download_size: 602412677
dataset_size: 602620189
- config_name: som
features:
- name: text
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
decode: false
- name: lang
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 1455941672
num_examples: 17354
download_size: 1437831373
dataset_size: 1455941672
- config_name: swahili
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: text
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 8763983905
num_examples: 412435
download_size: 5012049012
dataset_size: 8763983905
- config_name: swh
features:
- name: text
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
- name: audio
dtype:
audio:
decode: false
splits:
- name: train
num_bytes: 4763063290
num_examples: 146179
download_size: 4722484977
dataset_size: 4763063290
- config_name: wol
features:
- name: text
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
decode: false
- name: lang
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 4893866154
num_examples: 36691
download_size: 4661525784
dataset_size: 4893866154
- config_name: wolof
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: text
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 4275421272
num_examples: 36009
download_size: 4100478830
dataset_size: 4275421272
- config_name: yor
features:
- name: text
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
- name: audio
dtype:
audio:
decode: false
splits:
- name: train
num_bytes: 122881808
num_examples: 3451
download_size: 121281673
dataset_size: 122881808
- config_name: yoruba
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: text
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 25744535207
num_examples: 1648471
download_size: 22184723388
dataset_size: 25744535207
- config_name: zul
features:
- name: text
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
- name: audio
dtype:
audio:
decode: false
splits:
- name: train
num_bytes: 506360
num_examples: 16
download_size: 507173
dataset_size: 506360
configs:
- config_name: amh
data_files:
- split: train
path: amh/train-*
- config_name: amharic
data_files:
- split: train
path: amharic/train-*
- config_name: hau
data_files:
- split: train
path: hau/train-*
- config_name: hausa
data_files:
- split: train
path: hausa/train-*
- config_name: som
data_files:
- split: train
path: som/train-*
- config_name: swahili
data_files:
- split: train
path: swahili/train-*
- config_name: swh
data_files:
- split: train
path: swh/train-*
- config_name: wol
data_files:
- split: train
path: wol/train-*
- config_name: wolof
data_files:
- split: train
path: wolof/train-*
- config_name: yor
data_files:
- split: train
path: yor/train-*
- config_name: yoruba
data_files:
- split: train
path: yoruba/train-*
- config_name: zul
data_files:
- split: train
path: zul/train-*
---