more conf with preprocess.yaml

examples/aishell/s1/conf/chunk_conformer.yaml

@@ -15,7 +15,7 @@ collator:
   vocab_filepath: data/vocab.txt 
   unit_type: 'char'
   spm_model_prefix: ''
-  augmentation_config: conf/augmentation.json
+  augmentation_config: conf/preprocess.yaml
   batch_size: 32
   raw_wav: True  # use raw_wav or kaldi feature
   spectrum_type: fbank #linear, mfcc, fbank
@@ -38,7 +38,7 @@ collator:
 
 # network architecture
 model:
-    cmvn_file: "data/mean_std.json"
+    cmvn_file: 
     cmvn_file_type: "json"
     # encoder related
     encoder: conformer

examples/aishell/s1/conf/conformer.yaml

@@ -15,7 +15,7 @@ collator:
   vocab_filepath: data/vocab.txt 
   unit_type: 'char'
   spm_model_prefix: ''
-  augmentation_config: conf/augmentation.json
+  augmentation_config: conf/preprocess.yaml
   batch_size: 64
   raw_wav: True  # use raw_wav or kaldi feature
   spectrum_type: fbank #linear, mfcc, fbank
@@ -37,7 +37,7 @@ collator:
 
 # network architecture
 model:
-    cmvn_file: "data/mean_std.json"
+    cmvn_file: 
     cmvn_file_type: "json"
     # encoder related
     encoder: conformer

examples/aishell/s1/conf/preprocess.yaml

@@ -0,0 +1,29 @@
+process:
+  # extract kaldi fbank from PCM
+  - type: fbank_kaldi
+    fs: 16000
+    n_mels: 80
+    n_shift: 160
+    win_length: 400
+    dither: true
+  - type: cmvn_json
+    cmvn_path: data/mean_std.json
+  # 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/callcenter/s1/conf/chunk_conformer.yaml

@@ -15,7 +15,7 @@ collator:
   vocab_filepath: data/vocab.txt 
   unit_type: 'char'
   spm_model_prefix: ''
-  augmentation_config: conf/augmentation.json
+  augmentation_config: conf/preprocess.yaml
   batch_size: 32
   raw_wav: True  # use raw_wav or kaldi feature
   spectrum_type: fbank #linear, mfcc, fbank
@@ -38,7 +38,7 @@ collator:
 
 # network architecture
 model:
-    cmvn_file: "data/mean_std.json"
+    cmvn_file: 
     cmvn_file_type: "json"
     # encoder related
     encoder: conformer

examples/callcenter/s1/conf/conformer.yaml

@@ -15,7 +15,7 @@ collator:
   vocab_filepath: data/vocab.txt 
   unit_type: 'char'
   spm_model_prefix: ''
-  augmentation_config: conf/augmentation.json
+  augmentation_config: conf/preprocess.yaml
   batch_size: 32
   raw_wav: True  # use raw_wav or kaldi feature
   spectrum_type: fbank #linear, mfcc, fbank
@@ -37,7 +37,7 @@ collator:
 
 # network architecture
 model:
-    cmvn_file: "data/mean_std.json"
+    cmvn_file: 
     cmvn_file_type: "json"
     # encoder related
     encoder: conformer

examples/callcenter/s1/conf/preprocess.yaml

@@ -0,0 +1,29 @@
+process:
+  # extract kaldi fbank from PCM
+  - type: fbank_kaldi
+    fs: 16000
+    n_mels: 80
+    n_shift: 160
+    win_length: 400
+    dither: true
+  - type: cmvn_json
+    cmvn_path: data/mean_std.json
+  # 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/timit/s1/conf/preprocess.yaml

@@ -0,0 +1,29 @@
+process:
+  # extract kaldi fbank from PCM
+  - type: fbank_kaldi
+    fs: 16000
+    n_mels: 80
+    n_shift: 160
+    win_length: 400
+    dither: true
+  - type: cmvn_json
+    cmvn_path: data/mean_std.json
+  # 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/timit/s1/conf/transformer.yaml

@@ -14,7 +14,7 @@ collator:
   vocab_filepath: data/vocab.txt
   unit_type: "word"
   mean_std_filepath: ""
-  augmentation_config: ""
+  augmentation_config: conf/preprocess.yaml
   batch_size: 64
   raw_wav: True  # use raw_wav or kaldi feature
   spectrum_type: fbank #linear, mfcc, fbank
@@ -37,7 +37,7 @@ collator:
 
 # network architecture
 model:
-    cmvn_file: "data/mean_std.json"
+    cmvn_file: 
     cmvn_file_type: "json"
     # encoder related
     encoder: transformer