Menlo/raw-speech-whispervq-v2
收藏Hugging Face2024-08-30 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/Menlo/raw-speech-whispervq-v2
下载链接
链接失效反馈官方服务：
资源简介：
---
dataset_info:
- config_name: dutch
features:
- name: source
dtype: string
- name: tokens
sequence: int64
- name: index
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 3129087752
num_examples: 374287
download_size: 574575043
dataset_size: 3129087752
- config_name: english
features:
- name: source
dtype: string
- name: tokens
sequence: int64
- name: index
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 20134474501
num_examples: 2420047
download_size: 3786301162
dataset_size: 20134474501
- config_name: french
features:
- name: source
dtype: string
- name: tokens
sequence: int64
- name: index
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 2168482757
num_examples: 258213
download_size: 401737677
dataset_size: 2168482757
- config_name: german
features:
- name: source
dtype: string
- name: tokens
sequence: int64
- name: index
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 3957952347
num_examples: 469942
download_size: 701424594
dataset_size: 3957952347
- config_name: italian
features:
- name: source
dtype: string
- name: tokens
sequence: int64
- name: index
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 518527170
num_examples: 62133
download_size: 94846254
dataset_size: 518527170
- config_name: polish
features:
- name: source
dtype: string
- name: tokens
sequence: int64
- name: index
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 217204197
num_examples: 26083
download_size: 40512114
dataset_size: 217204197
- config_name: portuguese
features:
- name: source
dtype: string
- name: tokens
sequence: int64
- name: index
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 338470564
num_examples: 39230
download_size: 62422578
dataset_size: 338470564
- config_name: spanish
features:
- name: source
dtype: string
- name: tokens
sequence: int64
- name: index
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 1846859432
num_examples: 220701
download_size: 346253619
dataset_size: 1846859432
configs:
- config_name: dutch
data_files:
- split: train
path: dutch/train-*
- config_name: english
data_files:
- split: train
path: english/train-*
- config_name: french
data_files:
- split: train
path: french/train-*
- config_name: german
data_files:
- split: train
path: german/train-*
- config_name: italian
data_files:
- split: train
path: italian/train-*
- config_name: polish
data_files:
- split: train
path: polish/train-*
- config_name: portuguese
data_files:
- split: train
path: portuguese/train-*
- config_name: spanish
data_files:
- split: train
path: spanish/train-*
---
提供机构：
Menlo
