[WIP] Add phone based train and decode for gigaspeech

[yfyeung]

No description provided.

[wangtiance]

Hi, have you got any results with phone based models? I previously tried with librispeech and the result was worse than BPE. For pruned transducer I only got 4-5 WER for test-clean.

[yfyeung]

Hi, have you got any results with phone based models? I previously tried with librispeech and the result was worse than BPE. For pruned transducer I only got 4-5 WER for test-clean.

I tried the pruned transducer on gigaspeech M, and the result was worse than BPE too.

unit level	dev & test	lm	ngram-lm-scale	ppl	checkpoint
phone 76	13.15 & 13.46	3gram_pruned_1e8	0.235	192.176 & 213.068	epoch 30 avg 7
bpe 500	12.88 & 12.87	-	-	-	epoch 30 avg 8

[wangtiance]

Thanks! But your result seems very close. Will try your recipe on librispeech sometime.

[yfyeung]

Maybe sometime later. Not recently.

[pingfengluo]

@yfyeung can you update and merge this PR?