Two approaches
Two approaches for FST-based forced alignment will be described:
Note that the Kaldi-based approach does not depend on Kaldi at all. That is, you don’t need to install Kaldi in order to use it. Instead, we use kaldi-decoder, which has ported the C++ decoding code from Kaldi without depending on it.
Differences between the two approaches
The following table compares the differences between the two approaches.
Features |
Kaldi-based |
k2-based |
Support CUDA |
No |
Yes |
Support CPU |
Yes |
Yes |
Support batch processing |
No |
Yes on CUDA; No on CPU |
Support streaming models |
Yes |
No |
Support C++ APIs |
Yes |
Yes |
Support Python APIs |
Yes |
Yes |