Text To Music

🚀 探索预训练检查点在文本到音乐生成任务中的有效性

本项目是一个语言 - 音乐模型，能够直接根据自然语言描述生成完整且语义连贯的乐谱。通过在大量文本 - 音乐对上进行微调，该模型为文本条件下的符号音乐生成提供了新的解决方案。

🚀 快速开始

你可以在 Textune: Generating Tune from Text 上在线使用和体验这个语言 - 音乐模型。在这个在线平台上，你可以轻松输入所需的文本描述，并从模型获得生成的乐谱输出。

✨ 主要特性

• 基于真实数据训练：该模型在 282,870 对英文文本 - 音乐对上对 BART - base 进行微调，所有乐谱均以 ABC 记谱法表示。据我们所知，这是第一个在真实文本 - 音乐对上训练实现文本条件下符号音乐生成的模型，且音乐完全由模型生成，无需任何手工规则。
• 多风格音乐生成：能够生成多种风格的音乐，如蓝调、古典、民谣、爵士、流行和世界音乐等。所有生成的乐谱都可以用标准古典记谱法写在一个谱表上（用于声乐独唱或器乐独奏）。

📦 安装指南

由于版权原因，我们无法公开发布该模型的训练数据集。不过，我们提供了 WikiMusicText (WikiMT) 数据集，其中包含 1010 对文本 - 音乐数据，可用于评估语言 - 音乐模型的性能。

💻 使用示例

基础用法

以下是如何在 PyTorch 中使用该模型的示例代码：

import torch
from samplings import top_p_sampling, temperature_sampling
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained('sander-wood/text-to-music')
model = AutoModelForSeq2SeqLM.from_pretrained('sander-wood/text-to-music')
model = model

max_length = 1024
top_p = 0.9
temperature = 1.0

text = "This is a traditional Irish dance music."
input_ids = tokenizer(text, 
                      return_tensors='pt', 
                      truncation=True, 
                      max_length=max_length)['input_ids']

decoder_start_token_id = model.config.decoder_start_token_id
eos_token_id = model.config.eos_token_id

decoder_input_ids = torch.tensor([[decoder_start_token_id]])

for t_idx in range(max_length):
    outputs = model(input_ids=input_ids, 
    decoder_input_ids=decoder_input_ids)
    probs = outputs.logits[0][-1]
    probs = torch.nn.Softmax(dim=-1)(probs).detach().numpy()
    sampled_id = temperature_sampling(probs=top_p_sampling(probs, 
                                                           top_p=top_p, 
                                                           return_probs=True),
                                      temperature=temperature)
    decoder_input_ids = torch.cat((decoder_input_ids, torch.tensor([[sampled_id]])), 1)
    if sampled_id!=eos_token_id:
        continue
    else:
        tune = "X:1\n"
        tune += tokenizer.decode(decoder_input_ids[0], skip_special_tokens=True)
        print(tune)
        break

高级用法

以下是一些模型生成的示例，未经过筛选：

######################## INPUT TEXT ########################

This is a traditional Irish dance music.
Note Length-1/8
Meter-6/8
Key-D

####################### OUTPUT TUNES #######################

X:1
L:1/8
M:6/8
K:D
 A | BEE BEE | Bdf edB | BAF FEF | DFA BAF | BEE BEE | Bdf edB | BAF DAF | FED E2 :: A |
 Bef gfe | faf edB | BAF FEF | DFA BAF | Bef gfe | faf edB | BAF DAF | FED E2 :|

X:2
L:1/8
M:6/8
K:D
 A |: DED F2 A | d2 f ecA | G2 B F2 A | E2 F GFE | DED F2 A | d2 f ecA | Bgf edc |1 d3 d2 A :|2
 d3 d2 a || a2 f d2 e | f2 g agf | g2 e c2 d | e2 f gfe | fed gfe | agf bag | fed cde | d3 d2 a |
 agf fed | Adf agf | gfe ecA | Ace gfe | fed gfe | agf bag | fed cde | d3 d2 ||

X:3
L:1/8
M:6/8
K:D
 BEE BEE | Bdf edB | BAF FEF | DFA dBA | BEE BEE | Bdf edB | BAF FEF |1 DED DFA :|2 DED D2 e |:
 faf edB | BAF DFA | BAF FEF | DFA dBA | faf edB | BAF DFA | BdB AFA |1 DED D2 e :|2 DED DFA ||

######################## INPUT TEXT ########################

This is a jazz-swing lead sheet with chord and vocal.

####################### OUTPUT TUNES #######################

X:1
L:1/8
M:4/4
K:F
"F" CFG |"F" A6 z G |"Fm7" A3 G"Bb7" A3 G |"F" A6 z G |"F7" A4"Eb7" G4 |"F" F6 z F |
"Dm" A3 G"Dm/C" A3 G |"Bb" A2"Gm" B2"C7" G3 G |"F" F8- |"Dm7""G7" F6 z2 |"C" C4 C3 C |
"C7" C2 B,2"F" C4 |"F" C4 C3 C |"Dm" D2 C2"Dm/C" D4 |"Bb" D4 D3 D |"Bb" D2 C2"C7" D4 |"F" C8- |
"F" C4"Gm" z C"C7" FG |"F" A6 z G |"Fm7" A3 G"Bb7" A3 G |"F" A6 z G |"F7" A4"Eb7" G4 |"F" F6 z F |
"Dm" A3 G"Dm/C" A3 G |"Bb" A2"Gm" B2"C7" G3 G |"F" F8- |"F" F6 z2 |]

X:2
L:1/4
M:4/4
K:F
"^A""F" A3 A |"Am7" A2"D7" A2 |"Gm7" G2"C7" G A |"F" F4 |"F" A3 A |"Am7" A2"D7" A2 |"Gm7" G2"C7" G A |
"F" F4 |"Gm" B3 B |"Am7" B2"D7" B2 |"Gm" B2"D7" B A |"Gm7" G4 |"F" A3 A |"Am7" A2"D7" A2 |
"Gm7" G2"C7" G A |"F" F4 |"Bb7" F3 G |"F" A2 A2 |"Gm" B2"C7" B2 |"F" c2"D7" c c |"Gm7" c2"C7" B2 |
"F" A2"F7" A2 |"Bb" B2"F" B A |"Bb" B2"F" B A |"Gm" B2"F" B A |"Gm7" B2"F" B A |"Gm7" B2"F" B A |
"C7" B2 c2 |"F""Bb7" A4 |"F""Bb7" z4 |]

X:3
L:1/4
M:4/4
K:Bb
 B, ||"Gm""^A1" G,2 B, D |"D7" ^F A2 G/=F/ |"Gm" G2"Cm7" B c |"F7" A2 G =F |"Bb" D2 F A |
"Cm7" c e2 d/c/ |"Gm7" B3/2 G/-"C7" G2- |"F7" G2 z B, |"Gm""^B" G,2 B, D |"D7" ^F A2 G/=F/ |
"Gm" G2"Cm7" B c |"F7" A2 G =F |"Bb" D2 F A |"Cm7" c e2 d/c/ |"Gm7" B3/2 G/-"C7" G2- |"F7" G2 z2 ||
"^C""F7""^A2" F4- | F E D C |"Bb" D2 F B | d3 c/B/ |"F" A2"Cm7" G2 |"D7" ^F2 G2 |"Gm" B3"C7" A |
"F7" G4 ||"F7""^A3" F4- | F E D C |"Bb" D2 F B | d3 c/B/ |"F" A2"Cm7" G2 |"D7" ^F2 G2 |"Gm" B3 A |
"C7" G4 ||"^B""Gm""^C" B2 c B |"Cm" c B c B |"Gm7" c2 B A |"C7" B3 A |"Bb" B2 c B |"G7" d c B A |
"Cm" G2 A G |"F7" F2 z G ||"^C""F7" F F3 |"Bb" D D3 |"Cm" E E3 |"D7" ^F F3 |"Gm" G2 A B |"C7" d3 d |
"Gm" d3 d |"D7" d3 B, ||"^D""Gm" G,2 B, D |"D7" ^F A2 G/=F/ |"Gm" G2"Cm7" B c |"F7" A2 G =F |
"Bb" D2 F A |"Cm7" c e2 d/c/ |"Gm7" B3/2 G/-"C7" G2- |"F7" G2 z2 |]

######################## INPUT TEXT ########################

This is a Chinese folk song from the Jiangnan region. It was created during the Qianlong era (1735-1796) of the Qing dynasty. Over time, many regional variations were created, and the song gained popularity both in China and abroad. One version of the song describes a custom of giving jasmine flowers, popular in the southern Yangtze delta region of China.

####################### OUTPUT TUNES #######################

X:1
L:1/8
Q:1/4=100
M:2/4
K:C
"^Slow" DA A2 | GA c2- | c2 G2 | c2 GF | GA/G/ F2 | E2 DC | DA A2 | GA c2- | c2 GA | cd- d2 |
 cA c2- | c2 GA | cd- d2 | cA c2- | c2 GA | c2 A2 | c2 d2 | cA c2- | c2 c2 | A2 G2 | F2 AG | F2 ED |
 CA,/C/ D2- | D2 CD | F2 A2 | G2 ED | CG A2 | G2 FD | CA,/C/ D2- | D2 CD | F2 A2 | G2 ED |
 CG A2 | G2 FD | CA,/C/ D2- | D2 z2 :|

X:2
L:1/8
Q:1/4=100
M:2/4
K:C
"^ MDolce" Ac de | d2 AG | cA cd | A2 AG | E2 ED | CD E2- | E2 z2 | EG ed | c2 AG | cA cd |
 A2 AG | E2 ED | CD E2- | E2 z2 |"^ howeveroda" Ac de | d2 AG | cA cd | A2 AG | E2 ED | CD E2- |
 E2 z2 | A2 cA | GA E2- | E2 z2 | GA cd | e2 ed | cd e2- | e2 z2 | ge d2 | cd c2- | c2 z2 |
 Ac de | d2 AG | cA cd | A2 AG | E2 ED | CD E2- | E2 z2 | EG ed | c2 AG | cA cd | A2 AG | E2 ED |
 CD E2- | E2 z2 |"^DDtisata" Ac de | d2 AG | cA cd | A2 AG | E2 ED | CD E2- | E2 z2 | A2 cA |
 GA E2- | E2 z2 | GA cd | e2 ed | cd e2- | e2 z2 | ge d2 | cd c2- | c2 z2 | Ac de | d2 AG |
 cA cd | A2 AG | E2 ED | CD E2- | E2 z2 | Ac de | d2 AG | cA cd | A2 AG | E2 ED | CD E2- | E2 z2 |
 Ac de | d2 AG | cA cd | A2 AG | E2 ED | CD E2- | E2 z2 |"^  Easy" Ac de | d2 AG | cA cd |
 A2 AG | E2 ED | CD E2- | E2 z2 | Ac de | d2 AG | cA cd | A2 AG | E2 ED | CD E2- | E2 z2 |]

X:3
L:1/8
Q:1/4=60
M:4/4
K:C
"^S books defe.." AA A2 cdcc | AcAG A4- | A8 | A,4 CD C2 | A,4 cdcA | A2 GA- A4- | A2 GA A2 AA |
 AG E2 D2 C2 | D6 ED | C2 D4 C2 | D2 C2 D4 | C2 A,2 CD C2 | A,4 cdcA | A2 GA- A4- | A2 GA A2 AA |
 AG E2 D2 C2 | D6 z2 |]

📚 详细文档

预期用途与限制

• 用途：你可以使用该模型进行文本条件下的音乐生成。所有生成的乐谱都可以用标准古典记谱法写在一个谱表上（用于声乐独唱或器乐独奏），并且风格多样。我们建议使用 this repository 中的脚本进行推理。生成的曲调采用 ABC 记谱法，可以使用 this website 或 this software 将其转换为乐谱或音频。
• 限制：该模型的创造力有限，在需要高度创造力的任务（如旋律风格转换）上表现不佳，并且对输入敏感。更多信息请查看 our paper。

BibTeX 引用和引用信息

@inproceedings{
wu2023exploring,
title={Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task}, 
author={Shangda Wu and Maosong Sun},
booktitle={The AAAI-23 Workshop on Creative AI Across Modalities},
year={2023},
url={https://openreview.net/forum?id=QmWXskBhesn}
}

📄 许可证

本项目采用 MIT 许可证。