AdolfVonKleist
AdolfVonKleist
Is it possible to retrieve a probability, confidence or even raw score for each filled slot in a given intent response? Sometimes an utterance will produce multiple candidate resolutions for...
I am interested in recommended usage approach for reinsertion of a job on TTL expiry, where the reason is failure of the user app to call 'done' in time. This...
Hi I see that xapiand is released under MIT license, but appears to either directly contain or link the xapian core. What is the relationship there, and how do you...
The topic of LM training came up again recently. The aligner produces weighted alignment lattices. There is some evidence that augmenting the Maximization step in the EM alignment process with...
The purpose of this issue is to extend the ```phonetisaurus-train``` convenience script to support a wider range of well-known LM training toolkits, in addition to the backoff inclusion of a...
I'm looking for hints about how to correctly replicate the exact normalization process that is applied during simulated streaming with `decode.py` in `streaming_decode.py` for the streaming zipformer. I have been...
More efficient model serialization for this implementation. Currently still relies on vanilla RnnLM.
In the ARPA to WFSA conversion script, in the case of a unigram model, the final-state prob should be set to the sentence-end prob, if available; not just default to...
I've been using WhisperLive with great success recently in multiple languages. Seriously amazing. I recently noticed the support for `initial_prompt` which was added in January, and tried applying it to...