When using pocketsphinx_continuous, is it possible that will be differeneces in accuracy when recognizing from microphone vs. recognizing from a WAV file.
When shoud I use pocketsphinx_continuous, and when pocketsphinx_batch.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
When using pocketsphinx_continuous, is it possible that will be differeneces in accuracy when recognizing from microphone vs. recognizing from a WAV file.
Yes, if decoding is too slow live recognition might not be possible because recognizer skips audio chunks.
When shoud I use pocketsphinx_continuous, and when pocketsphinx_batch.
batch - for testing and tuning the decoding parameters, pocketsphinx_continuous - for decoding files.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Yes, if decoding is too slow live recognition might not be possible because recognizer skips audio chunks.
When using pocketsphinx on desktop or laptop running Windows, and pocketsphinx is the only app the user execute, is it possible that decoding will be too slow? (using today computers)
Last edit: Oren G. 2016-12-09
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
When using pocketsphinx_continuous, is it possible that will be differeneces in accuracy when recognizing from microphone vs. recognizing from a WAV file.
When shoud I use pocketsphinx_continuous, and when pocketsphinx_batch.
Yes, if decoding is too slow live recognition might not be possible because recognizer skips audio chunks.
batch - for testing and tuning the decoding parameters, pocketsphinx_continuous - for decoding files.
When using pocketsphinx on desktop or laptop running Windows, and pocketsphinx is the only app the user execute, is it possible that decoding will be too slow? (using today computers)
Last edit: Oren G. 2016-12-09
You can check the log output for processing time of each stage.