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-recognizer-transducer-impl.h

@@ -103,11 +103,21 @@ class OnlineRecognizerTransducerImpl : public OnlineRecognizerImpl {
       }
 
       decoder_ = std::make_unique<OnlineTransducerModifiedBeamSearchDecoder>(
-          model_.get(), lm_.get(), config_.max_active_paths,
-          config_.lm_config.scale, unk_id_, config_.blank_penalty);
+          model_.get(),
+          lm_.get(),
+          config_.max_active_paths,
+          config_.lm_config.scale,
+          unk_id_,
+          config_.blank_penalty,
+          config_.temperature_scale);
+
     } else if (config.decoding_method == "greedy_search") {
       decoder_ = std::make_unique<OnlineTransducerGreedySearchDecoder>(
-          model_.get(), unk_id_, config_.blank_penalty);
+          model_.get(),
+          unk_id_,
+          config_.blank_penalty,
+          config_.temperature_scale);
+
     } else {
       SHERPA_ONNX_LOGE("Unsupported decoding method: %s",
                        config.decoding_method.c_str());
@@ -141,11 +151,21 @@ class OnlineRecognizerTransducerImpl : public OnlineRecognizerImpl {
       }
 
       decoder_ = std::make_unique<OnlineTransducerModifiedBeamSearchDecoder>(
-          model_.get(), lm_.get(), config_.max_active_paths,
-          config_.lm_config.scale, unk_id_, config_.blank_penalty);
+          model_.get(),
+          lm_.get(),
+          config_.max_active_paths,
+          config_.lm_config.scale,
+          unk_id_,
+          config_.blank_penalty,
+          config_.temperature_scale);
+
     } else if (config.decoding_method == "greedy_search") {
       decoder_ = std::make_unique<OnlineTransducerGreedySearchDecoder>(
-          model_.get(), unk_id_, config_.blank_penalty);
+          model_.get(),
+          unk_id_,
+          config_.blank_penalty,
+          config_.temperature_scale);
+
     } else {
       SHERPA_ONNX_LOGE("Unsupported decoding method: %s",
                        config.decoding_method.c_str());