Loading...

Back to Details

music-emotion

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/music-emotion — Emotion & Style Analysis

/music-emotion — 情感与风格分析

Classify the emotional content of an audio file: primary mood, energy level, emotional valence, arousal, genre, and mood tags.

对音频文件的情感内容进行分类：主要情绪、能量等级、情感效价、唤醒度、流派以及情绪标签。

Usage

使用方法

/music-emotion <audio_file_path>

/music-emotion <audio_file_path>

Steps

步骤

Validate the audio file path
Run emotion analysis:

bash

python3 -m music_analyzer emotion "<audio_file_path>"

Present results:
- Primary Emotion: Dominant mood (happy, sad, calm, energetic, etc.)
- Energy Level: 0-1 scale with curve across song segments
- Valence: -1 (negative) to 1 (positive)
- Genre: Detected genre
- Mood Tags: Descriptive mood keywords

验证音频文件路径
运行情感分析：

bash

python3 -m music_analyzer emotion "<audio_file_path>"

展示结果：
- 主要情绪：主导情绪（开心、悲伤、平静、充满活力等）
- 能量等级：0-1的数值范围，包含歌曲各段落的变化曲线
- 情感效价：-1（消极）到1（积极）
- 流派：检测出的音乐流派
- 情绪标签：描述性的情绪关键词

Detection Methods

检测方法

CLAP (full tier): AI-based emotion/genre classification using CLAP model
Heuristic (lite tier): Spectral features + rhythm + tonality-based rules

The method used is noted in the

method

field of the output.

CLAP（完整层级）：基于CLAP模型的AI驱动情感/流派分类
启发式（轻量层级）：基于频谱特征+节奏+调性的规则

使用的方法会在输出的

method

字段中注明。

Output Fields

输出字段

Field	Description
`primary_emotion`	Dominant emotion label
`secondary_emotions`	Additional emotion tags
`overall_energy`	Energy level 0-1
`energy_curve`	Energy values per segment
`valence`	Emotional valence -1 to 1
`arousal`	Arousal level 0-1
`genre`	Detected genre
`mood_tags`	Mood descriptor keywords

字段	描述
`primary_emotion`	主导情绪标签
`secondary_emotions`	附加情绪标签
`overall_energy`	0-1范围的能量等级
`energy_curve`	各段落的能量值
`valence`	-1到1的情感效价
`arousal`	0-1范围的唤醒度
`genre`	检测出的流派
`mood_tags`	情绪描述关键词