Open lv-gh opened 4 years ago
Thanks for reporting. I would consider it a minor issue.
Well, it is a minor issue, but without modifying source code i can't use sphinx in this scenario: jsgf -> fsm -> OpenFst minimization (log arcs/weights) -> fsm2fsg.
Don't use jsgf, just build the language models. See also for details:
Thanks. Experiments shows that FSG works better. Besides it's a specific domain (valid/known address dictation; not much of a freedom to spell address differently that statistical language models would benefit)
test.gram:
jsgf weights > 1.0 are OK (and i suppose are pretty valid) to
jsgf_build_fsg_internal()
and that grammar can be used for decoding (-jsgf) and/or exported to fsg:But resulting fsg can't be loaded:
because
fsg_model_read()
requires all log weights/probabilities to be <= 1.0: