Track token scores (#571)
* add export of per-token scores (ys, lm, context) - for best path of the modified-beam-search decoding of transducer * refactoring JSON export of OnlineRecognitionResult, extending pybind11 API of OnlineRecognitionResult * export per-token scores also for greedy-search (online-transducer) - export un-scaled lm_probs (modified-beam search, online-transducer) - polishing * fill lm_probs/context_scores only if LM/ContextGraph is present (make Result smaller)
This commit is contained in:
1
.gitignore
vendored
1
.gitignore
vendored
@@ -1,6 +1,7 @@
|
||||
build
|
||||
*.zip
|
||||
*.tgz
|
||||
*.sw?
|
||||
onnxruntime-*
|
||||
icefall-*
|
||||
run.sh
|
||||
|
||||
Reference in New Issue
Block a user