amanuelbyte/african_speech_clean

---
dataset_info:
- config_name: amharic
features:
- name: text
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
splits:
- name: train
num_bytes: 20020186401
num_examples: 55660
download_size: 18264934277
dataset_size: 20020186401
- config_name: hausa
features:
- name: audio
dtype:
audio:
sampling_rate: 24000
- name: text
dtype: string
splits:
- name: train
num_bytes: 2759570290.72
num_examples: 1322
download_size: 2410109948
dataset_size: 2759570290.72
- config_name: somali
features:
- name: text
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: lang
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 1455941479
num_examples: 17354
download_size: 1437831250
dataset_size: 1455941479
- config_name: swahili
features:
- name: text
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
splits:
- name: train
num_bytes: 13522763655
num_examples: 558614
download_size: 9734426103
dataset_size: 13522763655
- config_name: swahili_clean
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: text
dtype: string
splits:
- name: train
num_bytes: 329583143
num_examples: 10000
download_size: 329697901
dataset_size: 329583143
- config_name: wolof
features:
- name: text
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: lang
dtype: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 9168860448
num_examples: 72700
download_size: 8761312082
dataset_size: 9168860448
- config_name: yoruba
features:
- name: text
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
splits:
- name: train
num_bytes: 25864326146
num_examples: 1651922
download_size: 22305974462
dataset_size: 25864326146
- config_name: yoruba_clean
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: text
dtype: string
splits:
- name: train
num_bytes: 925922141
num_examples: 10000
download_size: 925963597
dataset_size: 925922141
- config_name: zulu
features:
- name: text
dtype: string
- name: lang
dtype: string
- name: source
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
splits:
- name: train
num_bytes: 506360
num_examples: 16
download_size: 507188
dataset_size: 506360
configs:
- config_name: amharic
data_files:
- split: train
path: amharic/train-*
- config_name: hausa
data_files:
- split: train
path: hausa/train-*
- config_name: somali
data_files:
- split: train
path: somali/train-*
- config_name: swahili
data_files:
- split: train
path: swahili/train-*
- config_name: swahili_clean
data_files:
- split: train
path: swahili_clean/train-*
- config_name: wolof
data_files:
- split: train
path: wolof/train-*
- config_name: yoruba
data_files:
- split: train
path: yoruba/train-*
- config_name: yoruba_clean
data_files:
- split: train
path: yoruba_clean/train-*
- config_name: zulu
data_files:
- split: train
path: zulu/train-*
---