钢琴转谱技术（MP3转MIDI）

最新推荐文章于 2024-12-20 12:00:09 发布

木尧大兄弟

最新推荐文章于 2024-12-20 12:00:09 发布

阅读量4.5k

点赞数 2

分类专栏：技术杂记

本文链接：https://blog.csdn.net/muyao987/article/details/109632443

版权

技术杂记专栏收录该内容

75 篇文章

订阅专栏

代码(by 字节跳动孔大佬)：
https://github.com/qiuqiangkong/piano_transcription_inference

使用：

1.安装package

pip install piano_transcription_inference

2.下载预训练模型
https://zenodo.org/record/4034264

3.运行代码

from piano_transcription_inference import PianoTranscription, sample_rate, load_audio

# Load audio
(audio, _) = load_audio('piano.wav', sr=sample_rate, mono=True)

# Transcriptor
transcriptor = PianoTranscription(device='cpu', checkpoint_path='CRNN_note_F1=0.9677_pedal_F1=0.9186.pth')  # device: 'cuda' | 'cpu'

# Transcribe and write out to MIDI file
transcribed_dict = transcriptor.transcribe(audio, 'cut_liszt.mid')

运行结果
D:\python\Environment\Scripts\python.exe D:/pycharm_profession/Projects-professional/b20_summarization/钢琴转midi.py
Checkpoint path: CRNN_note_F1=0.9677_pedal_F1=0.9186.pth
Using cpu for inference.
Using CPU.
Segment 0 / 61
Segment 1 / 61
Segment 2 / 61
…
Segment 61 / 61
Write out to cut_liszt.mid