-
@lumaku Thank you so much for your incredible work. I've been working on obtaining word-level confidence scores for different ASR tools, aiming to compare Whisper and Wav2vec2 models. However, I've no…
-
sktime currently includes in ``sktime.transformers.series_as_features.pca`` a method of doing ordinary principal component analysis of a series. I do not believe that it is possible at the moment to u…
-
Hi,
Many thanks for your tool! I am working with nanopore signals collected from two different sources (`source_1 `and` source_2`), where I want to get their consensus. I have some questions regar…
-
微博内容精选
-
Using a weighted metric (e.g. WeightedSqEuclidean) for the dynamic time warping seems to not be possible as the weights passed to the distance are a vector, but in lines 190 and 199 in dtw.jl the cost…
-
### Describe the bug
occasionally, on small problems, k-medoids crashes with the trace below. We think somehow its forming empty clusters, but not sure at all why as yet. THis can be mitigated throug…
-
The memory requirement of DTW grows quadratically with the length of the input. The current approach may only be practical for source audio that's about up to 60 - 120 minutes long (with `low` granul…
-
Version [v1.0-beta.0.7](https://github.com/Xiangyu-Hu/SPHinXsys/releases/tag/v1.0-beta.0.7) with changelog:
> Riemann solver will still be used for fluid-wall interaction, since some cases occasion…
-
Hi, thanks for your work, it's really helpful!!!
I have a question about align.
when using faster-whisper, specific `word_timestamps=True` in `transcribe` method can obtain word timestamps, seems li…
-
The purpose of dtw.py is to generate a contribution matrix, but how to execute the dtw.py file? Can you give an example to execute the dtw.py file through different data sets? Do you need other code…