diff options
author | Paul B Mahol <onemda@gmail.com> | 2019-05-05 16:01:53 +0300 |
---|---|---|
committer | Paul B Mahol <onemda@gmail.com> | 2019-05-14 16:17:14 +0300 |
commit | f49cec2ba8830dd8df0ac73a39c118f6e20b06bd (patch) | |
tree | 8e2c26aa815ac1c989b13b76cf66acf95b4fe7bd /doc/filters.texi | |
parent | 670251de56cdcda0c32d588959c8ed2da09075a2 (diff) |
avfilter: add asr filter
Diffstat (limited to 'doc/filters.texi')
-rw-r--r-- | doc/filters.texi | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/doc/filters.texi b/doc/filters.texi index 697ffcb921..38c70bf674 100644 --- a/doc/filters.texi +++ b/doc/filters.texi @@ -2131,6 +2131,41 @@ It accepts the following values: Set additional parameter which controls sigmoid function. @end table +@section asr +Automatic Speech Recognition + +This filter uses PocketSphinx for speech recognition. To enable +compilation of this filter, you need to configure FFmpeg with +@code{--enable-pocketsphinx}. + +It accepts the following options: + +@table @option +@item rate +Set sampling rate of input audio. Defaults is @code{16000}. +This need to match speech models, otherwise one will get poor results. + +@item hmm +Set dictionary containing acoustic model files. + +@item dict +Set pronunciation dictionary. + +@item lm +Set language model file. + +@item lmctl +Set language model set. + +@item lmname +Set which language model to use. + +@item logfn +Set output for log messages. +@end table + +The filter exports recognized speech as the frame metadata @code{lavfi.asr.text}. + @anchor{astats} @section astats |