Closed desh2608 closed 8 months ago
Great!
@csukuangfj could you also check this when you have some time? Thanks!
@csukuangfj could you also check this when you have some time? Thanks!
Thanks! Left a minor comment. Otherwise, it looks good to me.
@csukuangfj could you also check this when you have some time? Thanks!
Thanks! Left a minor comment. Otherwise, it looks good to me.
Sorry it took a while since I was on vacation last 2 weeks. I have made the change.
Thanks!
This is an implementation of the HAT loss proposed in https://arxiv.org/abs/2003.07705.
The test produces reasonable looking losses. I am working on a LibriSpeech zipformer recipe using this loss. In general, it is not expected to improve upon the RNNT loss by itself, but may be useful for things like using external LMs. I am planning to use it in multi-talker ASR for speaker attribution (e.g. https://arxiv.org/abs/2309.08489)