From 785f3f0bcf3d65d3f00232e9c084c78d4bff5bc1 Mon Sep 17 00:00:00 2001
From: Zengwei Yao <yaozengwei@outlook.com>
Date: Tue, 9 Jul 2024 20:04:47 +0800
Subject: [PATCH] Update RESULTS.md, adding results and model links of
 zipformer-small/medium CTC/AED models (#1683)

---
 egs/librispeech/ASR/README.md  |   2 +-
 egs/librispeech/ASR/RESULTS.md | 113 ++++++++++++++++++++++++++++++++-
 2 files changed, 112 insertions(+), 3 deletions(-)

diff --git a/egs/librispeech/ASR/README.md b/egs/librispeech/ASR/README.md
index 93fef7a079..8b87ee19b4 100644
--- a/egs/librispeech/ASR/README.md
+++ b/egs/librispeech/ASR/README.md
@@ -50,7 +50,7 @@ We place an additional Conv1d layer right after the input embedding layer.
 | `conformer-ctc2`             | Reworked Conformer | Use auxiliary attention head |
 | `conformer-ctc3`             | Reworked Conformer | Streaming version + delay penalty |
 | `zipformer-ctc`              | Zipformer          | Use auxiliary attention head |
-| `zipformer`                  | Upgraded Zipformer | Use auxiliary transducer head | The latest recipe |
+| `zipformer`                  | Upgraded Zipformer | Use auxiliary transducer head / attention-decoder head | The latest recipe |
 
 # MMI
 
diff --git a/egs/librispeech/ASR/RESULTS.md b/egs/librispeech/ASR/RESULTS.md
index 6f00bc14d9..66b147764b 100644
--- a/egs/librispeech/ASR/RESULTS.md
+++ b/egs/librispeech/ASR/RESULTS.md
@@ -8,6 +8,117 @@ See <https://github.com/k2-fsa/icefall/pull/1389> for more details.
 
 #### Non-streaming
 
+##### small-scale model, number of model parameters: 46282107, i.e., 46.3 M
+
+You can find a pretrained model, training logs, decoding logs, and decoding results at:
+<https://huggingface.co/Zengwei/icefall-asr-librispeech-zipformer-small-ctc-attention-decoder-2024-07-09>
+
+You can use <https://github.com/k2-fsa/sherpa> to deploy it.
+
+| decoding method                      | test-clean | test-other | comment             |
+|--------------------------------------|------------|------------|---------------------|
+| ctc-decoding                         | 3.04       | 7.04       | --epoch 50 --avg 30 |
+| attention-decoder-rescoring-no-ngram | 2.45       | 6.08       | --epoch 50 --avg 30 |
+
+The training command is:
+```bash
+export CUDA_VISIBLE_DEVICES="0,1"
+# For non-streaming model training:
+./zipformer/train.py \
+  --world-size 2 \
+  --num-epochs 50 \
+  --start-epoch 1 \
+  --use-fp16 1 \
+  --exp-dir zipformer/exp-small \
+  --full-libri 1 \
+  --use-ctc 1 \
+  --use-transducer 0 \
+  --use-attention-decoder 1 \
+  --ctc-loss-scale 0.1 \
+  --attention-decoder-loss-scale 0.9 \
+  --num-encoder-layers 2,2,2,2,2,2 \
+  --feedforward-dim 512,768,768,768,768,768 \
+  --encoder-dim 192,256,256,256,256,256 \
+  --encoder-unmasked-dim 192,192,192,192,192,192 \
+  --base-lr 0.04 \
+  --max-duration 1700 \
+  --master-port 12345
+```
+
+The decoding command is:
+```bash
+export CUDA_VISIBLE_DEVICES="0"
+for m in ctc-decoding attention-decoder-rescoring-no-ngram; do
+  ./zipformer/ctc_decode.py \
+    --epoch 50 \
+    --avg 30 \
+    --exp-dir zipformer/exp-small \
+    --use-ctc 1 \
+    --use-transducer 0 \
+    --use-attention-decoder 1 \
+    --attention-decoder-loss-scale 0.9 \
+    --num-encoder-layers 2,2,2,2,2,2 \
+    --feedforward-dim 512,768,768,768,768,768 \
+    --encoder-dim 192,256,256,256,256,256 \
+    --encoder-unmasked-dim 192,192,192,192,192,192 \
+    --max-duration 100 \
+    --causal 0 \
+    --num-paths 100 \
+    --decoding-method $m
+done
+```
+
+##### medium-scale model, number of model parameters: 89987295, i.e., 90.0 M
+
+You can find a pretrained model, training logs, decoding logs, and decoding results at:
+<https://huggingface.co/Zengwei/icefall-asr-librispeech-zipformer-ctc-attention-decoder-2024-07-08>
+
+You can use <https://github.com/k2-fsa/sherpa> to deploy it.
+
+| decoding method                      | test-clean | test-other | comment             |
+|--------------------------------------|------------|------------|---------------------|
+| ctc-decoding                         | 2.46       | 5.57       | --epoch 50 --avg 22 |
+| attention-decoder-rescoring-no-ngram | 2.23       | 4.98       | --epoch 50 --avg 22 |
+
+The training command is:
+```bash
+export CUDA_VISIBLE_DEVICES="0,1,2,3"
+# For non-streaming model training:
+./zipformer/train.py \
+  --world-size 4 \
+  --num-epochs 50 \
+  --start-epoch 1 \
+  --use-fp16 1 \
+  --exp-dir zipformer/exp \
+  --full-libri 1 \
+  --use-ctc 1 \
+  --use-transducer 0 \
+  --use-attention-decoder 1 \
+  --ctc-loss-scale 0.1 \
+  --attention-decoder-loss-scale 0.9 \
+  --max-duration 1200 \
+  --master-port 12345
+```
+
+The decoding command is:
+```bash
+export CUDA_VISIBLE_DEVICES="0"
+for m in ctc-decoding attention-decoder-rescoring-no-ngram; do
+  ./zipformer/ctc_decode.py \
+    --epoch 50 \
+    --avg 22 \
+    --exp-dir zipformer/exp \
+    --use-ctc 1 \
+    --use-transducer 0 \
+    --use-attention-decoder 1 \
+    --attention-decoder-loss-scale 0.9 \
+    --max-duration 100 \
+    --causal 0 \
+    --num-paths 100 \
+    --decoding-method $m
+done
+```
+
 ##### large-scale model, number of model parameters: 174319650, i.e., 174.3 M
 
 You can find a pretrained model, training logs, decoding logs, and decoding results at:
@@ -15,8 +126,6 @@ You can find a pretrained model, training logs, decoding logs, and decoding resu
 
 You can use <https://github.com/k2-fsa/sherpa> to deploy it.
 
-Results of the CTC head:
-
 | decoding method                      | test-clean | test-other | comment             |
 |--------------------------------------|------------|------------|---------------------|
 | ctc-decoding                         | 2.29       | 5.14       | --epoch 50 --avg 29 |