checkpoints/acestep-captioner/README.md

---
license: mit
library_name: transformers
tags:
- music
- audio
---

<a href="https://arxiv.org/abs/2602.00744">Tech Report</a>

# ACE-Step Captioner

## Description

ACE-Step Captioner is the annotation model used by **ACE-Step v1.5** for training data labeling. It is a professional-grade music captioning model that generates detailed, structured descriptions of audio content.

### Performance

🏆 **Accuracy surpasses Gemini Pro 2.5** in music description tasks

### Key Features

- 🎼 **Musical Style Analysis** - Identifies genres, sub-genres, and stylistic influences
- 🎸 **Instrument Recognition** - Detects and describes 1000+ instrument types and combinations
- 🎭 **Structure & Progression** - Analyzes musical arrangement including intro, verse, chorus, bridge, climax, and outro
- 🔊 **Timbre Description** - Captures tonal qualities, textures, and sonic characteristics
- 📝 **Rich Vocabulary** - Supports 1000+ descriptive terms for comprehensive music annotation

## Usage

The usage is the same as [Qwen2.5 Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B).

### Prompt Format

Use the following prompt to caption audio:

```
*Task* Describe this audio in detail
<audio>
```

### Output Format

The model generates natural language descriptions covering multiple aspects of the music.

### Example Output

```
A melancholic indie folk track featuring fingerpicked acoustic guitar 
as the primary instrument. The song opens with a sparse, contemplative 
intro before the vocals enter with a breathy, intimate delivery. 
The arrangement gradually builds through the verse, adding subtle 
string pads and a gentle kick drum. The chorus lifts with layered 
harmonies and a warmer, fuller texture. The bridge introduces a 
key change and emotional climax before returning to the stripped-down 
acoustic arrangement for the outro.
```

## Descriptive Capabilities

### Musical Styles (Examples)

| Category | Styles |
|----------|--------|
| **Electronic** | Ambient, Techno, House, Drum & Bass, Synthwave, IDM, Downtempo |
| **Rock** | Alternative, Indie, Post-Rock, Progressive, Psychedelic, Grunge |
| **Pop** | Synth-pop, Electropop, Dream Pop, Art Pop, Indie Pop |
| **Classical** | Orchestral, Chamber, Minimalist, Neo-Classical, Cinematic |
| **World** | Latin, African, Middle Eastern, Asian Traditional, Celtic |
| **Jazz** | Fusion, Smooth, Bebop, Modal, Free Jazz |
| **Hip-Hop** | Trap, Boom Bap, Lo-fi, Instrumental, Cloud Rap |

### Instruments (1000+ Supported)

| Category | Examples |
|----------|----------|
| **Strings** | Acoustic Guitar, Electric Guitar, Violin, Cello, Bass, Harp, Mandolin |
| **Keys** | Piano, Synthesizer, Organ, Rhodes, Wurlitzer, Mellotron |
| **Percussion** | Drums, Electronic Drums, Congas, Bongos, Timpani, Vibraphone |
| **Wind** | Saxophone, Trumpet, Flute, Clarinet, Oboe, French Horn |
| **Electronic** | Synth Bass, Pad, Lead, Arpeggiator, Sampler, 808, 303 |

### Structure Analysis

- **Intro / Outro** - Opening and closing sections
- **Verse / Pre-Chorus / Chorus** - Main song structure
- **Bridge / Break** - Transitional sections
- **Build-up / Drop / Climax** - Dynamic progression
- **Interlude / Solo** - Instrumental passages

### Timbre Descriptions

| Dimension | Descriptors |
|-----------|-------------|
| **Texture** | Warm, Bright, Dark, Crisp, Muddy, Clean, Distorted, Saturated |
| **Space** | Reverberant, Dry, Spacious, Intimate, Cavernous, Tight |
| **Dynamics** | Punchy, Soft, Aggressive, Gentle, Compressed, Dynamic |
| **Character** | Ethereal, Gritty, Smooth, Raw, Polished, Organic, Synthetic |

## Use Cases

- **Music AI Training** - Generate high-quality captions for music generation models
- **Music Information Retrieval** - Create searchable metadata for audio databases
- **Content Moderation** - Analyze and categorize music content
- **Music Education** - Provide detailed analysis for learning purposes
- **Audio Production** - Document and describe sound design elements