Adding temperature scaling on Joiner logits: (#789)

* 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

sherpa-onnx/csrc/online-transducer-greedy-search-decoder.cc

@@ -144,6 +144,10 @@ void OnlineTransducerGreedySearchDecoder::Decode(
 
       // export the per-token log scores
       if (y != 0 && y != unk_id_) {
+        // apply temperature-scaling
+        for (int32_t n = 0; n < vocab_size; ++n) {
+          p_logit[n] /= temperature_scale_;
+        }
         LogSoftmax(p_logit, vocab_size);   // renormalize probabilities,
                                            // save time by doing it only for
                                            // emitted symbols