amine-khelif/mmlu_speech
收藏Hugging Face2025-12-05 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/amine-khelif/mmlu_speech
下载链接
链接失效反馈官方服务：
资源简介：
---
dataset_info:
features:
- name: audio
dtype:
audio:
sampling_rate: 24000
- name: answer
dtype: string
- name: category
dtype: string
splits:
- name: test
num_bytes: 24756216324.29
num_examples: 14267
download_size: 22260673427
dataset_size: 24756216324.29
configs:
- config_name: default
data_files:
- split: test
path: data/test-*
pretty_name: MMLU Speech
---
# MMLU Speech
Speech version of [MMLU](https://huggingface.co/datasets/cais/mmlu) eval, where the speech is synthesized using [XTTS-v2](https://huggingface.co/coqui/XTTS-v2). Note that there might not be a 1:1 mapping with the original text eval due to TTS failures.
提供机构：
amine-khelif
