Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
TensorSpeech
GitHub Repository: TensorSpeech/TensorFlowTTS
 Path: blob/master/examples/tacotron2/conf/tacotron2.synpaflex.v1.yaml
1559 views
1
# This is the hyperparameter configuration file for Tacotron2 v1.

2
# Please make sure this is adjusted for the LJSpeech dataset. If you want to

3
# apply to the other dataset, you might need to carefully change some parameters.

4
# This configuration performs 200k iters but 65k iters is enough to get a good models.

5


6
###########################################################

7
#                FEATURE EXTRACTION SETTING               #

8
###########################################################

9
hop_size: 256            # Hop size.

10
format: "npy"

11


12


13
###########################################################

14
#              NETWORK ARCHITECTURE SETTING               #

15
###########################################################

16
model_type: "tacotron2"

17


18
tacotron2_params:

19
    dataset: synpaflex

20
    embedding_hidden_size: 512

21
    initializer_range: 0.02

22
    embedding_dropout_prob: 0.1

23
    n_speakers: 1

24
    n_conv_encoder: 5

25
    encoder_conv_filters: 512

26
    encoder_conv_kernel_sizes: 5

27
    encoder_conv_activation: 'relu'

28
    encoder_conv_dropout_rate: 0.5

29
    encoder_lstm_units: 256

30
    n_prenet_layers: 2

31
    prenet_units: 256

32
    prenet_activation: 'relu'

33
    prenet_dropout_rate: 0.5

34
    n_lstm_decoder: 1

35
    reduction_factor: 1

36
    decoder_lstm_units: 1024

37
    attention_dim: 128

38
    attention_filters: 32

39
    attention_kernel: 31

40
    n_mels: 80

41
    n_conv_postnet: 5

42
    postnet_conv_filters: 512

43
    postnet_conv_kernel_sizes: 5

44
    postnet_dropout_rate: 0.1

45
    attention_type: "lsa"

46


47
###########################################################

48
#                  DATA LOADER SETTING                    #

49
###########################################################

50
batch_size: 32              # Batch size for each GPU with assuming that gradient_accumulation_steps == 1.

51
remove_short_samples: true # Whether to remove samples the length of which are less than batch_max_steps.

52
allow_cache: true           # Whether to allow cache in dataset. If true, it requires cpu memory.

53
mel_length_threshold: 32    # remove all targets has mel_length <= 32 

54
is_shuffle: true            # shuffle dataset after each epoch.

55
use_fixed_shapes: true      # use_fixed_shapes for training (2x speed-up)

56
                            # refer (https://github.com/dathudeptrai/TensorflowTTS/issues/34#issuecomment-642309118)

57


58
###########################################################

59
#             OPTIMIZER & SCHEDULER SETTING               #

60
###########################################################

61
optimizer_params:

62
    initial_learning_rate: 0.001

63
    end_learning_rate: 0.00001

64
    decay_steps: 150000          # < train_max_steps is recommend.

65
    warmup_proportion: 0.02

66
    weight_decay: 0.001

67
    

68
gradient_accumulation_steps: 1

69
var_train_expr: null  # trainable variable expr (eg. 'embeddings|decoder_cell' )

70
                      # must separate by |. if var_train_expr is null then we 

71
                      # training all variables.

72
###########################################################

73
#                    INTERVAL SETTING                     #

74
###########################################################

75
train_max_steps: 200000                 # Number of training steps.

76
save_interval_steps: 2000               # Interval steps to save checkpoint.

77
eval_interval_steps: 500                # Interval steps to evaluate the network.

78
log_interval_steps: 200                 # Interval steps to record the training log.

79
start_schedule_teacher_forcing: 200001  # don't need to apply schedule teacher forcing.

80
start_ratio_value: 0.5                  # start ratio of scheduled teacher forcing.

81
schedule_decay_steps: 50000             # decay step scheduled teacher forcing.

82
end_ratio_value: 0.0                    # end ratio of scheduled teacher forcing.

83
###########################################################

84
#                     OTHER SETTING                       #

85
###########################################################

86
num_save_intermediate_results: 1  # Number of results to be saved as intermediate results.

87


88