From aadd7cae42ba3af402321fdfcff6c8e93becb6d6 Mon Sep 17 00:00:00 2001
From: Fangjun Kuang <csukuangfj@gmail.com>
Date: Mon, 21 Feb 2022 15:11:46 +0800
Subject: [PATCH] Minor fixes.

---
 .../README.md                                 | 21 ++++----
 .../pretrained.py                             | 48 +++++++++----------
 .../test_decoder.py                           |  2 +-
 3 files changed, 38 insertions(+), 33 deletions(-)

diff --git a/egs/librispeech/ASR/transducer_stateless_multi_datasets/README.md b/egs/librispeech/ASR/transducer_stateless_multi_datasets/README.md
index 964bddfab..574fbf78e 100644
--- a/egs/librispeech/ASR/transducer_stateless_multi_datasets/README.md
+++ b/egs/librispeech/ASR/transducer_stateless_multi_datasets/README.md
@@ -8,15 +8,20 @@ You can use the following command to start the training:
 
 ```bash
 cd egs/librispeech/ASR
+./prepare.sh
+./prepare_giga_speech.sh
 
-export CUDA_VISIBLE_DEVICES="0,1,2,3"
+export CUDA_VISIBLE_DEVICES="0,1"
 
-./transducer_stateless/train.py \
-  --world-size 4 \
-  --num-epochs 30 \
+./transducer_stateless_multi_datasets/train.py \
+  --world-size 2 \
+  --num-epochs 60 \
   --start-epoch 0 \
-  --exp-dir transducer_stateless/exp \
-  --full-libri 1 \
-  --max-duration 250 \
-  --lr-factor 2.5
+  --exp-dir transducer_stateless_multi_datasets/exp-100 \
+  --full-libri 0 \
+  --max-duration 300 \
+  --lr-factor 1 \
+  --bpe-model data/lang_bpe_500/bpe.model \
+  --modified-transducer-prob 0.25
+  --giga-prob 0.2
 ```
diff --git a/egs/librispeech/ASR/transducer_stateless_multi_datasets/pretrained.py b/egs/librispeech/ASR/transducer_stateless_multi_datasets/pretrained.py
index ad8d89918..5ba3acea1 100755
--- a/egs/librispeech/ASR/transducer_stateless_multi_datasets/pretrained.py
+++ b/egs/librispeech/ASR/transducer_stateless_multi_datasets/pretrained.py
@@ -18,36 +18,36 @@
 Usage:
 
 (1) greedy search
-./transducer_stateless/pretrained.py \
-        --checkpoint ./transducer_stateless/exp/pretrained.pt \
-        --bpe-model ./data/lang_bpe_500/bpe.model \
-        --method greedy_search \
-        --max-sym-per-frame 1 \
-        /path/to/foo.wav \
-        /path/to/bar.wav \
+./transducer_stateless_multi_datasets/pretrained.py \
+    --checkpoint ./transducer_stateless_multi_datasets/exp/pretrained.pt \
+    --bpe-model ./data/lang_bpe_500/bpe.model \
+    --method greedy_search \
+    --max-sym-per-frame 1 \
+    /path/to/foo.wav \
+    /path/to/bar.wav
 
 (2) beam search
-./transducer_stateless/pretrained.py \
-        --checkpoint ./transducer_stateless/exp/pretrained.pt \
-        --bpe-model ./data/lang_bpe_500/bpe.model \
-        --method beam_search \
-        --beam-size 4 \
-        /path/to/foo.wav \
-        /path/to/bar.wav \
+./transducer_stateless_multi_datasets/pretrained.py \
+    --checkpoint ./transducer_stateless_multi_datasets/exp/pretrained.pt \
+    --bpe-model ./data/lang_bpe_500/bpe.model \
+    --method beam_search \
+    --beam-size 4 \
+    /path/to/foo.wav \
+    /path/to/bar.wav
 
 (3) modified beam search
-./transducer_stateless/pretrained.py \
-        --checkpoint ./transducer_stateless/exp/pretrained.pt \
-        --bpe-model ./data/lang_bpe_500/bpe.model \
-        --method modified_beam_search \
-        --beam-size 4 \
-        /path/to/foo.wav \
-        /path/to/bar.wav \
+./transducer_stateless_multi_datasets/pretrained.py \
+    --checkpoint ./transducer_stateless_multi_datasets/exp/pretrained.pt \
+    --bpe-model ./data/lang_bpe_500/bpe.model \
+    --method modified_beam_search \
+    --beam-size 4 \
+    /path/to/foo.wav \
+    /path/to/bar.wav
 
-You can also use `./transducer_stateless/exp/epoch-xx.pt`.
+You can also use `./transducer_stateless_multi_datasets/exp/epoch-xx.pt`.
 
-Note: ./transducer_stateless/exp/pretrained.pt is generated by
-./transducer_stateless/export.py
+Note: ./transducer_stateless_multi_datasets/exp/pretrained.pt is generated by
+./transducer_stateless_multi_datasets/export.py
 """
 
 
diff --git a/egs/librispeech/ASR/transducer_stateless_multi_datasets/test_decoder.py b/egs/librispeech/ASR/transducer_stateless_multi_datasets/test_decoder.py
index 3a653c1b7..9ee197ee8 100755
--- a/egs/librispeech/ASR/transducer_stateless_multi_datasets/test_decoder.py
+++ b/egs/librispeech/ASR/transducer_stateless_multi_datasets/test_decoder.py
@@ -19,7 +19,7 @@
 To run this file, do:
 
     cd icefall/egs/librispeech/ASR
-    python ./transducer_stateless/test_decoder.py
+    python ./transducer_stateless_multi_datasets/test_decoder.py
 """
 
 import torch