add preprocess.yaml

2 years ago · 61e565182a
parent e48e1d5e81
commit 61e565182a
5 changed files with 75 additions and 72 deletions
--- a/examples/aishell/asr0/conf/augmentation.json
+++ b/examples/aishell/asr0/conf/augmentation.json
@ -1,36 +0,0 @@
-[
-  {
-    "type": "speed",
-    "params": {
-      "min_speed_rate": 0.9,
-      "max_speed_rate": 1.1,
-      "num_rates": 3
-    },
-    "prob": 0.0
-  },
-  {
-    "type": "shift",
-    "params": {
-      "min_shift_ms": -5,
-      "max_shift_ms": 5
-    },
-    "prob": 1.0
-  },
-  {
-    "type": "specaug",
-    "params": {
-      "W": 0,
-      "warp_mode": "PIL",
-      "F": 10,
-      "n_freq_masks": 2,
-      "T": 50,
-      "n_time_masks": 2,
-      "p": 1.0,
-      "adaptive_number_ratio": 0,
-      "adaptive_size_ratio": 0,
-      "max_n_time_masks": 20,
-      "replace_with_zero": true
-    },
-    "prob": 1.0
-  }
-]
--- a/examples/aishell/asr0/conf/preprocess.yaml
+++ b/examples/aishell/asr0/conf/preprocess.yaml
@ -0,0 +1,25 @@
+process:
+  # extract kaldi fbank from PCM
+  - type: fbank_kaldi
+    fs: 16000
+    n_mels: 161
+    n_shift: 160
+    win_length: 400
+    dither: 0.1
+  - 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
--- a/examples/librispeech/asr0/conf/augmentation.json
+++ b/examples/librispeech/asr0/conf/augmentation.json
@ -1,36 +0,0 @@
-[
-  {
-    "type": "speed",
-    "params": {
-      "min_speed_rate": 0.9,
-      "max_speed_rate": 1.1,
-      "num_rates": 3
-    },
-    "prob": 0.0
-  },
-  {
-    "type": "shift",
-    "params": {
-      "min_shift_ms": -5,
-      "max_shift_ms": 5
-    },
-    "prob": 1.0
-  },
-  {
-    "type": "specaug",
-    "params": {
-      "W": 0,
-      "warp_mode": "PIL",
-      "F": 10,
-      "n_freq_masks": 2,
-      "T": 50,
-      "n_time_masks": 2,
-      "p": 1.0,
-      "adaptive_number_ratio": 0,
-      "adaptive_size_ratio": 0,
-      "max_n_time_masks": 20,
-      "replace_with_zero": true
-    },
-    "prob": 1.0
-  }
-]
--- a/examples/librispeech/asr0/conf/preprocess.yaml
+++ b/examples/librispeech/asr0/conf/preprocess.yaml
@ -0,0 +1,25 @@
+process:
+  # extract kaldi fbank from PCM
+  - type: fbank_kaldi
+    fs: 16000
+    n_mels: 161
+    n_shift: 160
+    win_length: 400
+    dither: 0.1
+  - 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
--- a/examples/tiny/asr0/conf/preprocess.yaml
+++ b/examples/tiny/asr0/conf/preprocess.yaml
@ -0,0 +1,25 @@
+process:
+  # extract kaldi fbank from PCM
+  - type: fbank_kaldi
+    fs: 16000
+    n_mels: 161
+    n_shift: 160
+    win_length: 400
+    dither: 0.1
+  - 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