From 68149cb9a7d39c14e95ada2979a4b7200eaf4902 Mon Sep 17 00:00:00 2001
From: Hui Zhang <zhtclz@foxmail.com>
Date: Tue, 22 Jun 2021 03:25:26 +0000
Subject: [PATCH] fix config for new datapipeline

---
 examples/aishell/s1/README.md                 |  2 +-
 examples/aishell/s1/conf/chunk_conformer.yaml | 15 +++++++++------
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/examples/aishell/s1/README.md b/examples/aishell/s1/README.md
index c306f8aa..601b0a8d 100644
--- a/examples/aishell/s1/README.md
+++ b/examples/aishell/s1/README.md
@@ -12,7 +12,7 @@
 ## Chunk Conformer
 
 | Model | Config | Augmentation| Test set | Decode method | Chunk | Loss | WER |  
-| --- | --- | --- | --- | --- | --- | --- | --- |   
+| --- | --- | --- | --- | --- | --- | --- | --- |  
 | conformer | conf/chunk_conformer.yaml | spec_aug + shift | test | attention | 16 | - | 0.061939 |  
 | conformer | conf/chunk_conformer.yaml | spec_aug + shift | test | ctc_greedy_search | 16 | - | 0.070806 |  
 | conformer | conf/chunk_conformer.yaml | spec_aug + shift | test | ctc_prefix_beam_search | 16 | - | 0.070739 |  
diff --git a/examples/aishell/s1/conf/chunk_conformer.yaml b/examples/aishell/s1/conf/chunk_conformer.yaml
index e626e106..0e5b8699 100644
--- a/examples/aishell/s1/conf/chunk_conformer.yaml
+++ b/examples/aishell/s1/conf/chunk_conformer.yaml
@@ -3,17 +3,20 @@ data:
   train_manifest: data/manifest.train
   dev_manifest: data/manifest.dev
   test_manifest: data/manifest.test
-  vocab_filepath: data/vocab.txt 
-  unit_type: 'char'
-  spm_model_prefix: ''
-  augmentation_config: conf/augmentation.json
-  batch_size: 32
   min_input_len: 0.5
   max_input_len: 20.0 # second
   min_output_len: 0.0
   max_output_len: 400.0
   min_output_input_ratio: 0.05
   max_output_input_ratio: 10.0
+  
+
+collator:
+  vocab_filepath: data/vocab.txt 
+  unit_type: 'char'
+  spm_model_prefix: ''
+  augmentation_config: conf/augmentation.json
+  batch_size: 32
   raw_wav: True  # use raw_wav or kaldi feature
   specgram_type: fbank #linear, mfcc, fbank
   feat_dim: 80
@@ -30,7 +33,7 @@ data:
   keep_transcription_text: False
   sortagrad: True 
   shuffle_method: batch_shuffle
-  num_workers: 0
+  num_workers: 2
 
 
 # network architecture
-- 
GitLab