TensorFlowASR/examples/conformer/config.yml at main · ebraraktas/TensorFlowASR · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
# Copyright 2020 Huy Le Nguyen (@usimarit)
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

speech_config:
  sample_rate: 16000
  frame_ms: 25
  stride_ms: 10
  num_feature_bins: 80
  feature_type: log_mel_spectrogram
  preemphasis: 0.97
  normalize_signal: True
  normalize_feature: True
  normalize_per_frame: False

decoder_config:
  vocabulary: ./vocabularies/librispeech/librispeech_train_4_1030.subwords
  target_vocab_size: 1000
  max_subword_length: 10
  blank_at_zero: True
  beam_width: 0
  norm_score: True
  corpus_files:
    - /mnt/h/ML/Datasets/ASR/Raw/LibriSpeech/train-clean-100/transcripts.tsv

model_config:
  name: conformer
  encoder_subsampling:
    type: conv2d
    filters: 144
    kernel_size: 3
    strides: 2
  encoder_positional_encoding: sinusoid
  encoder_dmodel: 144
  encoder_num_blocks: 16
  encoder_head_size: 36
  encoder_num_heads: 4
  encoder_mha_type: relmha
  encoder_kernel_size: 32
  encoder_fc_factor: 0.5
  encoder_dropout: 0.1
  prediction_embed_dim: 320
  prediction_embed_dropout: 0
  prediction_num_rnns: 1
  prediction_rnn_units: 320
  prediction_rnn_type: lstm
  prediction_rnn_implementation: 2
  prediction_layer_norm: True
  prediction_projection_units: 0
  joint_dim: 320
  prejoint_linear: True
  joint_activation: tanh
  joint_mode: add

learning_config:
  train_dataset_config:
    use_tf: True
    augmentation_config:
      feature_augment:
        time_masking:
          num_masks: 10
          mask_factor: 100
          p_upperbound: 0.05
        freq_masking:
          num_masks: 1
          mask_factor: 27
    data_paths:
      - /mnt/h/ML/Datasets/ASR/Raw/LibriSpeech/train-clean-100/transcripts.tsv
    tfrecords_dir: /mnt/h/ML/Datasets/ASR/Raw/LibriSpeech/tfrecords_1030
    shuffle: True
    cache: True
    buffer_size: 100
    drop_remainder: True
    stage: train

  eval_dataset_config:
    use_tf: True
    data_paths: null
    tfrecords_dir: /mnt/h/ML/Datasets/ASR/Raw/LibriSpeech/tfrecords_1030
    shuffle: False
    cache: True
    buffer_size: 100
    drop_remainder: True
    stage: eval

  test_dataset_config:
    use_tf: True
    data_paths: null
    tfrecords_dir: null
    shuffle: False
    cache: True
    buffer_size: 100
    drop_remainder: True
    stage: test

  optimizer_config:
    warmup_steps: 40000
    beta_1: 0.9
    beta_2: 0.98
    epsilon: 1e-9

  running_config:
    batch_size: 2
    num_epochs: 50
    checkpoint:
      filepath: /mnt/e/Models/local/conformer/checkpoints/{epoch:02d}.h5
      save_best_only: True
      save_weights_only: True
      save_freq: epoch
    states_dir: /mnt/e/Models/local/conformer/states
    tensorboard:
      log_dir: /mnt/e/Models/local/conformer/tensorboard
      histogram_freq: 1
      write_graph: True
      write_images: True
      update_freq: epoch
      profile_batch: 2