From 9d93d63cf2f7f7214892a8fb9d9c9c9feb4067ad Mon Sep 17 00:00:00 2001
From: Bailey Machiko Hirota <53164945+baileyeet@users.noreply.github.com>
Date: Fri, 18 Jul 2025 18:04:12 +0900
Subject: [PATCH] Update RESULTS.md

---
 egs/multi_ja_en/ASR/RESULTS.md | 40 +++++++++++++++++++++++++---------
 1 file changed, 30 insertions(+), 10 deletions(-)

diff --git a/egs/multi_ja_en/ASR/RESULTS.md b/egs/multi_ja_en/ASR/RESULTS.md
index 0f6996013..524726441 100644
--- a/egs/multi_ja_en/ASR/RESULTS.md
+++ b/egs/multi_ja_en/ASR/RESULTS.md
@@ -8,20 +8,19 @@ The training command is:
 
 ```shell
 ./zipformer/train.py \
-  --bilingual 1 \
   --world-size 4 \
-  --num-epochs 30 \
+  --num-epochs 21 \
   --start-epoch 1 \
   --use-fp16 1 \
   --exp-dir zipformer/exp \
-  --max-duration 600
+  --manifest-dir data/manifests
 ```
 
 The decoding command is:
 
 ```shell
 ./zipformer/decode.py \
-    --epoch 28 \
+    --epoch 21 \
     --avg 15 \
     --exp-dir ./zipformer/exp \
     --max-duration 600 \
@@ -31,8 +30,14 @@ The decoding command is:
 To export the model with onnx:
 
 ```shell
-./zipformer/export-onnx.py   --tokens data/lang_bbpe_2000/tokens.txt   --use-averaged-model 0   --epoch 35   --avg 1   --exp-dir zipformer/exp   --num-encoder-layers "2,2,3,4,3,2"   --downsampling-factor "1,2,4,8,4,2"   --feedforward-dim "512,768,1024,1536,1024,768"   --num-heads "4,4,4,8,4,4"   --encoder-dim "192,256,384,512,384,256"   --query-head-dim 32   --value-head-dim 12   --pos-head-dim 4   --pos-dim 48   --encoder-unmasked-dim "192,192,256,256,256,192"   --cnn-module-kernel "31,31,15,15,15,31"   --decoder-dim 512   --joiner-dim 512   --causal False   --chunk-size "16,32,64,-1"   --left-context-frames "64,128,256,-1"   --fp16 True
+./zipformer/export-onnx.py \
+  --tokens ./data/lang/bbpe_2000/tokens.txt \
+  --use-averaged-model 0 \
+  --epoch 21 \
+  --avg 1 \
+  --exp-dir ./zipformer/exp
 ```
+
 Word Error Rates (WERs) listed below:
 
 |       Datasets       | ReazonSpeech |  ReazonSpeech |     LibriSpeech    |    LibriSpeech    |
@@ -42,11 +47,26 @@ Word Error Rates (WERs) listed below:
 | modified_beam_search |    4.87      |     3.61      |        3.28        |       8.07        |
 
 
-Character Error Rates (CERs) for Japanese listed below:
-|   Decoding Method    | In-Distribution CER | JSUT | CommonVoice | TEDx  |
-| :------------------: | :-----------------: | :--: | :---------: | :---: | 
-|    greedy search     |        12.56        | 6.93 |    9.75     | 9.67  | 
-| modified beam search |        11.59        | 6.97 |    9.55     | 9.51  | 
+
+We also include WER% for common English ASR datasets:
+
+| Corpus                       | WER (%) |
+|-----------------------------|---------|
+| LibriSpeech (test-clean)    | 3.49    |
+| LibriSpeech (test-other)    | 7.64    |
+| CommonVoice                 | 39.87   |
+| TED                         | 23.92   |
+| MLS English (test-clean)    | 10.16   |
+
+
+And CER% for common Japanese datasets:
+
+| Corpus        | CER (%) |
+|---------------|---------|
+| JSUT          | 10.04   |
+| CommonVoice   | 10.39   |
+| TEDx          | 12.22   |
+
 
 Pre-trained model can be found here: https://huggingface.co/reazon-research/reazonspeech-k2-v2-ja-en/tree/main