theodorr/gigaspeech_full_filtered_3fbc6c4f

---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: segment_id
dtype: string
- name: speaker
dtype: string
- name: original_text
dtype: string
- name: begin_time
dtype: float32
- name: end_time
dtype: float32
- name: audio_id
dtype: string
- name: title
dtype: string
- name: url
dtype: string
- name: source
dtype:
class_label:
names:
'0': audiobook
'1': podcast
'2': youtube
- name: category
dtype:
class_label:
names:
'0': People and Blogs
'1': Business
'2': Nonprofits and Activism
'3': Crime
'4': History
'5': Pets and Animals
'6': News and Politics
'7': Travel and Events
'8': Kids and Family
'9': Leisure
'10': N/A
'11': Comedy
'12': News and Politics
'13': Sports
'14': Arts
'15': Science and Technology
'16': Autos and Vehicles
'17': Science and Technology
'18': People and Blogs
'19': Music
'20': Society and Culture
'21': Education
'22': Howto and Style
'23': Film and Animation
'24': Gaming
'25': Entertainment
'26': Travel and Events
'27': Health and Fitness
'28': audiobook
- name: original_full_path
dtype: string
- name: continuation
dtype: string
- name: audio_latent
list:
list:
list: float32
- name: audio_duration
dtype: float64
- name: text
dtype: string
splits:
- name: train
num_bytes: 28153231806
num_examples: 3259221
- name: test
num_bytes: 34696941
num_examples: 4000
download_size: 26231928079
dataset_size: 28187928747
---