v1.0.0: Faster Loading, Python3, Grammar/Rule Weights, and more
Support is now included in dragonfly2 v0.18.0! You can try a self-contained distribution available below, of either stable or development versions.
Notes
- Direct Parsing: parse recognitions directly on the FST, removing the (slow)
pyparsingdependency.- Caster example: Loading is now ~50% faster when cached, and the Kaldi backend accounts for only ~15% of loading time.
- Python3: both python 2 and 3 should be fully supported now.
- Unicode: this should also fix unicode issues in various places in both python2/3.
- Grammar/Rule Weights: can specify weight, where grammars/rules with higher weight value are more likely to be recognized, compared to their peers, for an ambiguous recognition.
- Generalized Alternative Dictation: the cloud dictation feature has been generalized to make it easier to add other alternatives in the future.
- Various bug fixes & optimizations
Artifacts
kaldi_model_zamia: A compatible general English Kaldi nnet3 chain model.kaldi-dragonfly-winpython: [stable release version] A self-contained, portable, batteries-included (python & libraries & model) distribution of kaldi-active-grammar + dragonfly2. Just unzip and run!kaldi-dragonfly-winpython-dev: [more recent development version] A self-contained, portable, batteries-included (python & libraries & model) distribution of kaldi-active-grammar + dragonfly2. Just unzip and run!kaldi-caster-winpython-dev: [more recent development version] A self-contained, portable, batteries-included (python & libraries & model) distribution of kaldi-active-grammar + dragonfly2 + caster. Just unzip and run!
If you have trouble downloading, try using wget --continue.
Donations are appreciated to encourage development.
[GitHub is currently matching all my donations
