asr-malayalam/indicvoices-v1a

---
dataset_info:
features:
- name: audio_filepath
dtype: string
- name: text
dtype: string
- name: duration
dtype: float64
- name: lang
dtype: string
- name: samples
dtype: int64
- name: verbatim
dtype: string
- name: normalized
dtype: string
- name: speaker_id
dtype: string
- name: scenario
dtype: string
- name: task_name
dtype: string
- name: gender
dtype: string
- name: age_group
dtype: string
- name: job_type
dtype: string
- name: qualification
dtype: string
- name: area
dtype: string
- name: district
dtype: string
- name: state
dtype: string
- name: occupation
dtype: string
- name: verification_report
struct:
- name: bad_extempore_quality
dtype: bool
- name: book_read
dtype: bool
- name: chatter_intermittent
dtype: bool
- name: chatter_persistent
dtype: bool
- name: comments
dtype: string
- name: decision
dtype: string
- name: duplicate_speaker
dtype: bool
- name: echo_present
dtype: bool
- name: factual_inaccuracy
dtype: bool
- name: incorrect_text_prompt
dtype: bool
- name: long_pauses
dtype: bool
- name: low_volume
dtype: bool
- name: mispronunciation
dtype: bool
- name: noise_intermittent
dtype: bool
- name: noise_persistent
dtype: bool
- name: objectionable_content
dtype: bool
- name: off_topic
dtype: bool
- name: reading_prompt
dtype: bool
- name: repeating_content
dtype: bool
- name: skipping_words
dtype: bool
- name: sst
dtype: bool
- name: stretching
dtype: bool
- name: unclear_audio
dtype: bool
- name: wrong_age_group
dtype: bool
- name: wrong_gender
dtype: bool
- name: wrong_language
dtype: bool
- name: audio
struct:
- name: array
sequence: float32
- name: sampling_rate
dtype: int64
splits:
- name: train
num_bytes: 13743705254
num_examples: 27812
- name: val
num_bytes: 240626301
num_examples: 416
download_size: 6834140884
dataset_size: 13984331555
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: val
path: data/val-*
---