aishell egs

examples/aishell/conf/augmentation.config

@@ -0,0 +1,8 @@
+[
+    {
+        "type": "shift",
+        "params": {"min_shift_ms": -5,
+                   "max_shift_ms": 5},
+        "prob": 1.0
+    }
+]

examples/aishell/conf/deepspeech2.yaml

@@ -0,0 +1,51 @@
+# https://yaml.org/type/float.html
+data:
+  train_manifest: data/manifest.train
+  dev_manifest: data/manifest.dev
+  test_manifest: data/manifest.test
+  mean_std_filepath: data/mean_std.npz
+  vocab_filepath: data/vocab.txt 
+  augmentation_config: conf/augmentation.config
+  batch_size: 16 # one gpu
+  max_duration: 27.0
+  min_duration: 0.0
+  specgram_type: linear
+  target_sample_rate: 16000
+  max_freq: None
+  n_fft: None
+  stride_ms: 10.0
+  window_ms: 20.0
+  use_dB_normalization: True
+  target_dB: -20
+  random_seed: 0
+  keep_transcription_text: False
+  sortagrad: True 
+  shuffle_method: batch_shuffle
+  num_workers: 0
+model:
+  num_conv_layers: 2
+  num_rnn_layers: 3
+  rnn_layer_size: 1024
+  use_gru: True 
+  share_rnn_weights: False 
+training:
+  n_epoch: 20
+  lr: 5e-4
+  weight_decay: 1e-06
+  global_grad_clip: 400.0
+  max_iteration: 500000
+  plot_interval: 1000
+  save_interval: 1000
+  valid_interval: 1000
+decoding:
+  batch_size: 128
+  error_rate_type: wer
+  decoding_method: ctc_beam_search
+  lang_model_path: models/lm/common_crawl_00.prune01111.trie.klm
+  alpha: 2.5
+  beta: 0.3
+  beam_size: 500
+  cutoff_prob: 1.0
+  cutoff_top_n: 40
+  num_proc_bsearch: 8
+

examples/aishell/models

@@ -0,0 +1 @@
+../../models