Audio Course documentation

Check your understanding of the course material

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Check your understanding of the course material

1. 采样率使用的单位是?

2. 使用流式加载模式加载大规模数据集时,何时才能开始使用该数据集?

3. 什么是时频谱?

4. 下列方法中,最简单的可以将原始音频转化为Whisper模型接受的对数梅尔谱的方法是?

A.

librosa.feature.melspectrogram(audio["array"])

B.

feature_extractor = WhisperFeatureExtractor.from_pretrained("openai/whisper-small")
feature_extractor(audio["array"])

C.

dataset.feature(audio["array"], model="whisper")

5. 如何从🤗 Hub加载数据集?

A.

from datasets import load_dataset

dataset = load_dataset(DATASET_NAME_ON_HUB)

B.

import librosa

dataset = librosa.load(PATH_TO_DATASET)

C.

from transformers import load_dataset

dataset = load_dataset(DATASET_NAME_ON_HUB)

6. 你的自定义数据集包含了32千赫兹采样率的高清音频。你现在想要训练一个使用16千赫兹采样率的语音识别模型。你应该怎么做?

7. 如何将机器学习模型生成的时频谱转化为波形?

< > Update on GitHub