xuning / sherpaonnx

Signed-off-by: manickavela1998@gmail.com <manickavela1998@gmail.com>

* Install naudiodon2 manually.

It is needed only when using a microphone. The CI tests don't need it.

Co-authored-by: Hao You <13182720519@sina.cn>

Update to match the changes in infer_sv.py at 3D-speaker. 

Added 2 more supported models and "zh_en" language.

* Adding temperature scaling on Joiner logits:

- T hard-coded to 2.0
- so far best result NCE 0.122 (still not so high)
    - the BPE scores were rescaled with 0.2 (but then also incorrect words
      get high confidence, visually reasonable histograms are for 0.5 scale)
    - BPE->WORD score merging done by min(.) function
      (tried also prob-product, and also arithmetic, geometric, harmonic mean)

- without temperature scaling (i.e. scale 1.0), the best NCE was 0.032 (here product merging was best)

Results seem consistent with: https://arxiv.org/abs/2110.15222

Everything tuned on a very-small set of 100 sentences with 813 words and 10.2% WER, a Czech model.

I also experimented with blank posteriors mixed into the BPE confidences,
but no NCE improvement found, so not pushing that.

Temperature scling added also to the Greedy search confidences.

* making `temperature_scale` configurable from outside