Update results.

README.md

@@ -35,6 +35,9 @@ We do provide a Colab notebook for this recipe.
 
 ### LibriSpeech
 
+Please see <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/README.md>
+for the **latest** results.
+
 We provide 4 models for this recipe:
 
 - [conformer CTC model][LibriSpeech_conformer_ctc]
@@ -92,6 +95,20 @@ in the decoding.
 
 We provide a Colab notebook to run a pre-trained transducer conformer + stateless decoder model: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1CO1bXJ-2khDckZIW8zjOPHGSKLHpTDlp?usp=sharing)
 
+
+#### k2 pruned RNN-T
+
+|     | test-clean | test-other |
+|-----|------------|------------|
+| WER | 2.57       | 5.95       |
+
+#### k2 pruned RNN-T + GigaSpeech
+
+|     | test-clean | test-other |
+|-----|------------|------------|
+| WER | 2.19       | 4.97       |
+
+
 ### Aishell
 
 We provide two models for this recipe: [conformer CTC model][Aishell_conformer_ctc]

egs/librispeech/ASR/RESULTS.md

@@ -127,6 +127,29 @@ The Nbest oracle WER is computed using the following steps:
   - 5. The path with the lowest edit distance is the final output and is used to
        compute the WER
 
+The command to compute the Nbest oracle WER is:
+
+```bash
+for epoch in 27; do
+  for avg in 10 ; do
+    for num_paths in 50 100 200 400; do
+      for nbest_scale in 0.5 0.8 1.0; do
+        ./pruned_transducer_stateless3/decode.py \
+            --epoch $epoch \
+            --avg $avg \
+            --exp-dir ./pruned_transducer_stateless3/exp \
+            --max-duration 600 \
+            --decoding-method fast_beam_search_nbest_oracle \
+            --num-paths $num_paths \
+            --max-states 32 \
+            --beam 8 \
+            --nbest-scale $nbest_scale
+      done
+    done
+  done
+done
+```
+
 ### LibriSpeech BPE training results (Pruned Transducer 2)
 
 [pruned_transducer_stateless2](./pruned_transducer_stateless2)