From b119cfe06dbb3f3fea136cca678cd148c5ed67b2 Mon Sep 17 00:00:00 2001
From: Hui Zhang <zhtclz@foxmail.com>
Date: Wed, 24 Nov 2021 06:42:35 +0000
Subject: [PATCH] fix preprocess of libri asr2

---
 .../librispeech/asr1/conf/chunk_transformer.yaml |  4 ++--
 examples/librispeech/asr2/conf/preprocess.yaml   | 16 ++++++++++++++++
 examples/librispeech/asr2/conf/transformer.yaml  |  2 +-
 3 files changed, 19 insertions(+), 3 deletions(-)
 create mode 100644 examples/librispeech/asr2/conf/preprocess.yaml

diff --git a/examples/librispeech/asr1/conf/chunk_transformer.yaml b/examples/librispeech/asr1/conf/chunk_transformer.yaml
index fe533777..c2644daf 100644
--- a/examples/librispeech/asr1/conf/chunk_transformer.yaml
+++ b/examples/librispeech/asr1/conf/chunk_transformer.yaml
@@ -11,9 +11,9 @@ data:
   max_output_input_ratio: 100.0
 
 collator:
-  vocab_filepath: data/vocab.txt 
+  vocab_filepath: data/lang_char/vocab.txt 
   unit_type: 'spm'
-  spm_model_prefix: 'data/bpe_unigram_5000'
+  spm_model_prefix: 'data/lang_char/bpe_unigram_5000'
   mean_std_filepath: ""
   augmentation_config: conf/preprocess.yaml
   batch_size: 64
diff --git a/examples/librispeech/asr2/conf/preprocess.yaml b/examples/librispeech/asr2/conf/preprocess.yaml
new file mode 100644
index 00000000..bc86d98c
--- /dev/null
+++ b/examples/librispeech/asr2/conf/preprocess.yaml
@@ -0,0 +1,16 @@
+process:
+  # these three processes are a.k.a. SpecAugument
+  - type: time_warp
+    max_time_warp: 5
+    inplace: true
+    mode: PIL
+  - type: freq_mask
+    F: 30
+    n_mask: 2
+    inplace: true
+    replace_with_zero: false
+  - type: time_mask
+    T: 40
+    n_mask: 2
+    inplace: true
+    replace_with_zero: false
diff --git a/examples/librispeech/asr2/conf/transformer.yaml b/examples/librispeech/asr2/conf/transformer.yaml
index de1ac347..4a50183a 100644
--- a/examples/librispeech/asr2/conf/transformer.yaml
+++ b/examples/librispeech/asr2/conf/transformer.yaml
@@ -57,7 +57,7 @@ collator:
   batch_frames_in: 0
   batch_frames_out: 0
   batch_frames_inout: 0
-  augmentation_config: conf/augmentation.json
+  augmentation_config: conf/preprocess.yaml 
   num_workers: 0
   subsampling_factor: 1
   num_encs: 1