ylacombe/libritts_r_tags

---
dataset_info:
- config_name: clean
features:
- name: text
dtype: string
- name: text_original
dtype: string
- name: speaker_id
dtype: string
- name: path
dtype: string
- name: chapter_id
dtype: string
- name: id
dtype: string
- name: speaking_rate
dtype: float64
- name: phonemes
dtype: string
- name: snr
dtype: float32
- name: c50
dtype: float32
- name: utterance_pitch_mean
dtype: float32
- name: utterance_pitch_std
dtype: float32
- name: gender
dtype: string
splits:
- name: dev.clean
num_bytes: 3316014
num_examples: 5736
- name: test.clean
num_bytes: 2950089
num_examples: 4837
- name: train.clean.100
num_bytes: 19408462
num_examples: 33232
- name: train.clean.360
num_bytes: 69116680
num_examples: 116426
download_size: 41317594
dataset_size: 94791245
- config_name: default
features:
- name: text
dtype: string
- name: text_original
dtype: string
- name: speaker_id
dtype: string
- name: path
dtype: string
- name: chapter_id
dtype: string
- name: id
dtype: string
- name: speaking_rate
dtype: float64
- name: phonemes
dtype: string
- name: snr
dtype: float32
- name: c50
dtype: float32
- name: utterance_pitch_mean
dtype: float32
- name: utterance_pitch_std
dtype: float32
- name: gender
dtype: string
splits:
- name: dev.clean
num_bytes: 3316014
num_examples: 5736
- name: test.clean
num_bytes: 2950089
num_examples: 4837
- name: train.clean.100
num_bytes: 19408462
num_examples: 33232
- name: train.clean.360
num_bytes: 69116680
num_examples: 116426
download_size: 41317594
dataset_size: 94791245
- config_name: other
features:
- name: text
dtype: string
- name: text_original
dtype: string
- name: speaker_id
dtype: string
- name: path
dtype: string
- name: chapter_id
dtype: string
- name: id
dtype: string
- name: utterance_pitch_mean
dtype: float32
- name: utterance_pitch_std
dtype: float32
- name: snr
dtype: float64
- name: c50
dtype: float64
- name: speaking_rate
dtype: float64
- name: phonemes
dtype: string
- name: gender
dtype: string
splits:
- name: dev.other
num_bytes: 2561145
num_examples: 4613
- name: test.other
num_bytes: 2759200
num_examples: 5120
- name: train.other.500
num_bytes: 117808485
num_examples: 205035
download_size: 52518135
dataset_size: 123128830
configs:
- config_name: clean
data_files:
- split: dev.clean
path: clean/dev.clean-*
- split: test.clean
path: clean/test.clean-*
- split: train.clean.100
path: clean/train.clean.100-*
- split: train.clean.360
path: clean/train.clean.360-*
- config_name: default
data_files:
- split: dev.clean
path: data/dev.clean-*
- split: test.clean
path: data/test.clean-*
- split: train.clean.100
path: data/train.clean.100-*
- split: train.clean.360
path: data/train.clean.360-*
- config_name: other
data_files:
- split: dev.other
path: other/dev.other-*
- split: test.other
path: other/test.other-*
- split: train.other.500
path: other/train.other.500-*
---

原始信息汇总

数据集概述

配置信息

配置名称：clean

• 特征列表：
  • text: string
  • text_original: string
  • speaker_id: string
  • path: string
  • chapter_id: string
  • id: string
  • speaking_rate: float64
  • phonemes: string
  • snr: float32
  • c50: float32
  • utterance_pitch_mean: float32
  • utterance_pitch_std: float32
  • gender: string
• 数据分割：
  • dev.clean: 3316014 字节, 5736 样本
  • test.clean: 2950089 字节, 4837 样本
  • train.clean.100: 19408462 字节, 33232 样本
  • train.clean.360: 69116680 字节, 116426 样本
• 下载大小：41317594 字节
• 数据集大小：94791245 字节

配置名称：default

• 特征列表：
  • text: string
  • text_original: string
  • speaker_id: string
  • path: string
  • chapter_id: string
  • id: string
  • speaking_rate: float64
  • phonemes: string
  • snr: float32
  • c50: float32
  • utterance_pitch_mean: float32
  • utterance_pitch_std: float32
  • gender: string
• 数据分割：
  • dev.clean: 3316014 字节, 5736 样本
  • test.clean: 2950089 字节, 4837 样本
  • train.clean.100: 19408462 字节, 33232 样本
  • train.clean.360: 69116680 字节, 116426 样本
• 下载大小：41317594 字节
• 数据集大小：94791245 字节

配置名称：other

• 特征列表：
  • text: string
  • text_original: string
  • speaker_id: string
  • path: string
  • chapter_id: string
  • id: string
  • utterance_pitch_mean: float32
  • utterance_pitch_std: float32
  • snr: float64
  • c50: float64
  • speaking_rate: float64
  • phonemes: string
  • gender: string
• 数据分割：
  • dev.other: 2561145 字节, 4613 样本
  • test.other: 2759200 字节, 5120 样本
  • train.other.500: 117808485 字节, 205035 样本
• 下载大小：52518135 字节
• 数据集大小：123128830 字节

数据文件路径

配置名称：clean

• 数据文件：
  • dev.clean: clean/dev.clean-*
  • test.clean: clean/test.clean-*
  • train.clean.100: clean/train.clean.100-*
  • train.clean.360: clean/train.clean.360-*

配置名称：default

• 数据文件：
  • dev.clean: data/dev.clean-*
  • test.clean: data/test.clean-*
  • train.clean.100: data/train.clean.100-*
  • train.clean.360: data/train.clean.360-*

配置名称：other

• 数据文件：
  • dev.other: other/dev.other-*
  • test.other: other/test.other-*
  • train.other.500: other/train.other.500-*