Merge pull request #1026 from zh794390558/asr2

[asr] fix preprocess of libri asr2

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

examples/librispeech/asr2/conf/preprocess.yaml

+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

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