A.HEBA

@luomingshuang ; We start working on your PR, thank you very much for the integration, Just to understand, why you still call the graph HLG ? and not TLG ?,...

@luomingshuang , I just run the full exp, and saw: ``` Test-clean: %WER 2005.99 [ 52557 / 2620, 49941 ins, 0 del, 2616 sub ] %SER 100.00 [ 2620 /...

> @luomingshuang , I just run the full exp, and saw: > > ``` > Test-clean: > %WER 2005.99 [ 52557 / 2620, 49941 ins, 0 del, 2616 sub ]...

> > @luomingshuang , I just run the full exp, and saw: > > ``` > > Test-clean: > > %WER 2005.99 [ 52557 / 2620, 49941 ins, 0 del,...

thanks @luomingshuang , I'm able to have same results with `torch=1.8`. After adding our `CategoricalLabel_encoding`, I will move to 1.10.. Let me highlight a small problem where I think we...

Hello @csukuangfj , @luomingshuang , Thanks you for the tricks. from my side, it seems not working; Two errors: 1st one if I consider @csukuangfj tricks: ``` Removing disambiguation symbols...

> > So the HLG compile, but in the decoding phase, I have an error when using the HLG.fst > > > It seems that the intersect between H_L_G is...

Let me start pushing the final updates for handling `CategoricalEncoder`, @csukuangfj, @luomingshuang , is there a comparaison between you `ctc_topo` and the one proposed by Miao in EESEN?

let add: - [ ] Logging duration, num segments... - [ ] Evaluate adding shards & webdatasets - [ ] CTC recipe

Hello, We have a similar implementation within speechbrain (implemented with Python-Numba), you can take a look https://github.com/speechbrain/speechbrain/tree/develop/recipes/LibriSpeech/ASR/transducer transducer implementation: https://github.com/speechbrain/speechbrain/blob/develop/speechbrain/nnet/loss/transducer_loss.py otherwise, you have the torchaudio supporting this lib within torchaudio...