Kira-Floris/Afrivoice_Swahili_ASR

---
dataset_info:
- config_name: agriculture
features:
- name: key
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: duration
dtype: float32
- name: instruction
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
splits:
- name: train
num_bytes: 77372073550.68
num_examples: 119871
- name: test
num_bytes: 229539618.0
num_examples: 352
- name: validation
num_bytes: 203080035.0
num_examples: 319
download_size: 73309766078
dataset_size: 77804693203.68
- config_name: education
features:
- name: key
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: duration
dtype: float32
- name: instruction
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
splits:
- name: train
num_bytes: 43967286790.92
num_examples: 66123
- name: test
num_bytes: 536016773.0
num_examples: 811
- name: validation
num_bytes: 499213555.0
num_examples: 757
download_size: 41933913267
dataset_size: 45002517118.92
- config_name: financial
features:
- name: key
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: duration
dtype: float32
- name: instruction
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
splits:
- name: train
num_bytes: 64732234300.88
num_examples: 101681
- name: test
num_bytes: 685487346.2
num_examples: 1040
- name: validation
num_bytes: 688137023.352
num_examples: 1034
download_size: 63963019064
dataset_size: 66105858670.43199
- config_name: government
features:
- name: key
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: duration
dtype: float32
- name: instruction
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
splits:
- name: train
num_bytes: 62455104347.8
num_examples: 96888
- name: test
num_bytes: 657872160.0
num_examples: 982
- name: validation
num_bytes: 598865047.0
num_examples: 892
download_size: 60132389278
dataset_size: 63711841554.8
- config_name: health
features:
- name: key
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: duration
dtype: float32
- name: instruction
dtype: string
- name: answer
dtype: string
- name: category
dtype: string
splits:
- name: train
num_bytes: 71785257447.48
num_examples: 106261
- name: test
num_bytes: 340042892.0
num_examples: 516
- name: validation
num_bytes: 397967181.0
num_examples: 619
download_size: 64107727051
dataset_size: 72523267520.48
configs:
- config_name: agriculture
data_files:
- split: train
path: agriculture/train-*
- split: test
path: agriculture/test-*
- split: validation
path: agriculture/validation-*
- config_name: education
data_files:
- split: train
path: education/train-*
- split: test
path: education/test-*
- split: validation
path: education/validation-*
- config_name: financial
data_files:
- split: train
path: financial/train-*
- split: test
path: financial/test-*
- split: validation
path: financial/validation-*
- config_name: government
data_files:
- split: train
path: government/train-*
- split: test
path: government/test-*
- split: validation
path: government/validation-*
- config_name: health
data_files:
- split: train
path: health/train-*
- split: test
path: health/test-*
- split: validation
path: health/validation-*
---