Skip to content

Releases: openvpi/dataset-tools

20241020.18

20 Oct 10:23
Compare
Choose a tag to compare

20241020.01

19 Oct 17:02
Compare
Choose a tag to compare

minlabel的json新增key isCheck,用于识别是否人工检查过

20240822.22

22 Aug 14:58
Compare
Choose a tag to compare
SlurCutter: added mouse hover crosshair

20240702.14

02 Jul 06:44
Compare
Choose a tag to compare

fix FBL bug

20240621.21

21 Jun 13:57
Compare
Choose a tag to compare

Currently, FoxBreatheLabeler only supports annotating breathing using TextGrid files output from SOFA(i.e. overlaying new "AP" annotations on intervals already marked as "SP").

Warning: When using Sofa to output tg files, the parameter “--ap_detector NoneAPDetector” must be added.

For details, please refer to the How to use project 0 in the Python version.

The Python version can use CUDA acceleration and requires self installation of the Torch environment.

Download Fbl Model

Python version

FblModel

16 Jun 17:01
Compare
Choose a tag to compare

FoxBreatheLabeler目前仅支持基于SOFA输出的TextGrid文件标注呼吸(即在已标为“SP”的区间覆盖上新的“AP”标注)。

将fbl_model.zip中的fbl_model文件夹拖放至Dataset-tool根目录即可(结构层次为Dataset-tool/fbl_model/model.onnx),fbl_model文件夹包括model.onnx、config.yaml两个文件。

20240513

13 May 12:42
Compare
Choose a tag to compare

ASR results can be saved as pinyin.

20240426.0

25 Apr 16:15
Compare
Choose a tag to compare

Add phoneme display in SlurCutter #6

This is a feature request from Discord. Phonemes are shown if the pre-condition is met: word count (by the number of non-slur notes) equals the length of ph_num array. Then phonemes are shown below the notes. New options are added in right-click menu as well.
Screenshot 2024-04-16 at 11 57 02 PM

20240422.12

22 Apr 03:56
Compare
Choose a tag to compare

Add LyricFA, only supports Chinese & Wav File < 40s.
Download Asr Model
cpp doc

Python version
Python version doc

20240422.0 Beta

21 Apr 16:02
Compare
Choose a tag to compare

Add LyricFA, only supports Chinese & Wav File < 40s.
Download Asr Model

Python version
Python version doc