Update README.md
Browse files
README.md
CHANGED
@@ -1,21 +1,29 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
---
|
4 |
# 🎵 GhostAI Music Generator 🎸
|
5 |
|
6 |
-
|
7 |
|
8 |
-
|
9 |
|
10 |
-
|
11 |
-
- **AI-Powered Music Generation**: Generate instrumental tracks in multiple genres using the `musicgen-medium` model.
|
12 |
-
- **Structured Song Sections**: Create tracks with distinct intros, verses, and choruses by using varied prompts for each chunk.
|
13 |
-
- **Gradio Web Interface**: Easily input prompts, adjust generation settings, and preview your music through an intuitive UI.
|
14 |
-
- **MP3 Output**: Save your tracks as high-quality MP3 files (320 kbps) with embedded metadata.
|
15 |
-
- **Audio Processing**: Enhance your music with EQ, a chorus effect for richness, and limiting to control peaks while preserving dynamics.
|
16 |
|
17 |
-
|
18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
1. **Clone the Repository**:
|
21 |
-
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# 🎵 GhostAI Music Generator 🎸
|
2 |
|
3 |
+
Welcome to the GhostAI Music Generator! This web-based tool utilizes Meta AI's `musicgen-medium` model to craft high-quality instrumental tracks across genres such as Rock, Techno, Jazz, Classical, and Hip-Hop. The application structures compositions with sections like intros, verses, and choruses, all accessible through an intuitive Gradio interface. Outputs are high-quality MP3 files at 320 kbps, complete with embedded metadata. To enhance audio quality, we've integrated processing features including equalization (EQ), a chorus effect, and peak limiting for a polished sound.
|
4 |
|
5 |
+
## Project Evolution and Optimization
|
6 |
|
7 |
+
Initially, the project faced VRAM limitations on an NVIDIA RTX 3060 Ti with 7.69 GiB. To address this, we divided 30-second tracks into manageable chunks—first into three 10-second segments, then into two 15-second segments—to optimize memory usage. The Bark model was removed to focus solely on instrumental generation, and we standardized the output format to MP3 for broader compatibility. To achieve a more natural song flow, we varied prompts for each chunk. For instance, the first chunk might use "dynamic intro and expressive verse," while the second employs "powerful chorus and energetic outro," providing a realistic song structure.
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
+
Audio enhancements include:
|
10 |
+
- **EQ**: Low-pass filter at 6000 Hz and high-pass filter at 100 Hz.
|
11 |
+
- **Chorus Effect**: 20ms delay with a -4 dB gain.
|
12 |
+
- **Peak Limiting**: Strict limiting at -8.0 dB to control peaks.
|
13 |
+
- **Gain Adjustment**: +2 dB boost before crossfading to address amplitude dips.
|
14 |
+
- **Compression**: Removed to preserve dynamic range.
|
15 |
+
|
16 |
+
## System Requirements
|
17 |
+
|
18 |
+
To get started, ensure your system meets the following requirements:
|
19 |
+
- **Operating System**: Ubuntu (Note: Windows/macOS are untested).
|
20 |
+
- **GPU**: CUDA-capable GPU with at least 8 GB VRAM.
|
21 |
+
- **Python**: Version 3.10.
|
22 |
+
- **ffmpeg**: Installed for audio processing.
|
23 |
+
|
24 |
+
## Installation and Setup
|
25 |
|
26 |
1. **Clone the Repository**:
|
27 |
+
```bash
|
28 |
+
git clone https://huggingface.co/your-username/ghostai-music-generator
|
29 |
+
cd ghostai-music-generator
|