Closed housebaby closed 3 years ago
Hello @danpovey https://github.com/danpovey It is obeserved from chain model output that the "output probability" is kind of flat, compared to CTC sharp peak .
Yes, this is expected...
I wonder how include-log-softmax would affect model performance , and why it is not used in the default config.
This wouldn't make a difference as the objective function is invariant to it. Dan
If we add softmax , is it possible to improve the decoding speed, as the output probability will be more discriminative so that more unlikely paths will be pruned? Thank you.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/4316, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAZFLO3XOZVKSAFFFVNSKSDSNYVJPANCNFSM4TG66ITQ .
This wouldn't make a difference as the objective function is invariant to it. Dan
If include-log-softmax=true won't make any difference, then which part can be tuned to make the probability more discrimitive in chain model? Thank you very much.
"discriminative" is not well defined here.. it depends what your purpose is.
On Mon, Nov 2, 2020 at 12:12 PM housebaby notifications@github.com wrote:
This wouldn't make a difference as the objective function is invariant to it. Dan
If include-log-softmax=true won't make any difference, then which part can be tuned to make the probability more discrimitive in chain model? Thank you very much.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/4316#issuecomment-720225802, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAZFLO2ZWORUFARR22SS7ELSNYWRDANCNFSM4TG66ITQ .
Sorry for the ambiguity. I mean, is it possible to make output probability in chain more sharp and less flat ( like CTC) , so that more unlikely paths will be pruned in decoding, thus making the decoding process faster? I wonder whether it is reasonable to think in this way
"discriminative" is not well defined here.. it depends what your purpose is. … On Mon, Nov 2, 2020 at 12:12 PM housebaby @.***> wrote: This wouldn't make a difference as the objective function is invariant to it. Dan If include-log-softmax=true won't make any difference, then which part can be tuned to make the probability more discrimitive in chain model? Thank you very much. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#4316 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAZFLO2ZWORUFARR22SS7ELSNYWRDANCNFSM4TG66ITQ .
It would be necessary to train with CTC as part of the objective. Not easy with current code, partly because of the interaction with context-dependency which makes it a little non-trivial to do it in a sensible way.
Dan
On Mon, Nov 2, 2020 at 1:21 PM housebaby notifications@github.com wrote:
Sorry for the ambiguity. I mean, is it possible to make output probability in chain more sharp and less flat ( like CTC) , so that more unlikely paths will be pruned in decoding, thus making the decoding process faster? I wonder whether it is reasonable to think in this way
"discriminative" is not well defined here.. it depends what your purpose is. … <#m-3348007015380785837> On Mon, Nov 2, 2020 at 12:12 PM housebaby @.***> wrote: This wouldn't make a difference as the objective function is invariant to it. Dan If include-log-softmax=true won't make any difference, then which part can be tuned to make the probability more discrimitive in chain model? Thank you very much. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#4316 (comment) https://github.com/kaldi-asr/kaldi/issues/4316#issuecomment-720225802>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAZFLO2ZWORUFARR22SS7ELSNYWRDANCNFSM4TG66ITQ .
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/4316#issuecomment-720242255, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAZFLO3PAXXGZCLJVK4K5LTSNY6TZANCNFSM4TG66ITQ .
I am closing this issue. As it stands, it's not easily doable.
Hello @danpovey It is obeserved from chain model output that the "output probability" is kind of flat, compared to CTC sharp peak . I wonder how include-log-softmax=true would affect model performance , and why it is not used in the default config. If we add softmax , is it possible to improve the decoding speed, as the output probability will be more discriminative so that more unlikely paths will be pruned? Thank you.