• Stars
    star
    207
  • Rank 188,607 (Top 4 %)
  • Language
  • Created over 2 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Opencpop: A High-Quality Open Source Chinese Popular Song Database for Singing Voice Synthesis

Opencpop

Official website | Paper

What is opencpop?

Opencpop, a publicly available high-quality Mandarin singing corpus, is designed for singing voice synthesis (SVS) systems. This corpus consists of 100 unique Mandarin songs, which were recorded by a professional female singer. All audio files were recorded with studio-quality at a sampling rate of 44,100 Hz in a professional recording studio environment.

All singing recordings have been phonetically annotated with utterance/note/phoneme boundaries and pitch types. The final dataset contains 3,756 utterances, with a total of about 5.2 hours. The testing set consists of 5 randomly chosen songs, and baseline synthesized results are provided.

The human voice is one of the most beautiful instruments. Let’s create usable singing voice synthesis technology for humanity. Enjoy!

Download

Download Link. Wish you can stay tuned to this project or to the official website for the latest updates. Thank you!

More Repositories

1

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit
Python
4,073
star
2

speech-synthesis-paper

List of speech synthesis papers.
987
star
3

wespeaker

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
Python
657
star
4

WenetSpeech

A 10000+ hours dataset for Chinese speech recognition
Shell
488
star
5

WeTextProcessing

Text Normalization & Inverse Text Normalization
Python
443
star
6

wekws

Production First and Production Ready End-to-End Keyword Spotting Toolkit
Python
430
star
7

wetts

Production First and Production Ready End-to-End Text-to-Speech Toolkit
Python
367
star
8

speech-recognition-papers

Towards hot directions in industrial end to end speech recognition
325
star
9

wenet-kws

Production First and Production Ready End-to-End Keyword Spotting Toolkit
Python
142
star
10

west

We Speech Transcript based on LLM, in 300 lines of code.
Python
109
star
11

wesignal

Production first, nn-based on-device signal processing toolkit.
63
star
12

WeTextProcessing.deprecated

C++
61
star
13

wesubtitle

用 OCR 提取视频硬字幕
Python
54
star
14

llm-papers

List of Large Lanugage Model Papers
51
star
15

wesep

Target Speaker Extraction Toolkit
Python
42
star
16

wecut

video cut powered by AI
25
star
17

WeSpeech-AI

Open Source Speech/Text Data on AI
18
star
18

nn-singal-processing-papers

List of NN based singal processing papers
17
star
19

wenet_in_action_homework

WeNet 实战课程作业
Python
16
star
20

wenet-e2e.github.io

WeNet Community
CSS
1
star
21

wenet-contributors

Contributors of WeNet, including individual and companies.
1
star