Compute sentence prob #93
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
I'm wondering whether it might make more sense to add this in Kaldi instead?
It seems to me that it's independent of where the LM comes from.
Remind me why we needed this.
Also, please use SRILM to verify that it's correct. SRILM has an option to
compute the probs per word.
…On Thu, Jul 5, 2018 at 4:51 PM, DongjiGao ***@***.***> wrote:
Add get_sentence_prob.py that can compute sentence probability from input
text file given language model in arpa form. The result would be written to
an output file.
------------------------------
You can view, comment on, or merge this pull request online at:
#93
Commit Summary
- add get_sentence_prob.py that can compute sentecne probability given
arpa lm
- small fix on output format
File Changes
- *A* scripts/get_sentence_prob.py
<https://github.com/danpovey/pocolm/pull/93/files#diff-0> (143)
Patch Links:
- https://github.com/danpovey/pocolm/pull/93.patch
- https://github.com/danpovey/pocolm/pull/93.diff
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#93>, or mute the thread
<https://github.com/notifications/unsubscribe-auth/ADJVuzS9yt-TAdd8OJKZRV2VeTBQ8Dowks5uDnxsgaJpZM4VEhiW>
.
|
|
Xiaohui needs a script to compute sentence probability like get_data_probs.py in pocolm. |
|
OK, thanks. When you've checked it, though, please show it to Xiaohui and
he can incorporate it into what he's doing directly, as a script that's in
Kaldi. I think this may make more sense.
…On Thu, Jul 5, 2018 at 8:45 PM, DongjiGao ***@***.***> wrote:
Xiaohui needs a script to compute sentence probability like
get_data_probs.py in pocolm.
#92 <#92>
I have checked several sentences by hand and they seem correct. I will
check with SRILM.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#93 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/ADJVuzarbaJpmLe8aG4-oXqml8DPRQx9ks5uDrMagaJpZM4VEhiW>
.
|
|
Will do. It might take me some time since I have not used SRILM before. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add get_sentence_prob.py that can compute sentence probability from input text file given language model in arpa form. The result would be written to an output file.