Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
TensorSpeech
GitHub Repository: TensorSpeech/TensorFlowTTS
 Path: blob/master/examples/fastspeech2/conf/fastspeech2.kss.v1.yaml
1559 views
1
# This is the hyperparameter configuration file for FastSpeech2 v1.

2
# Please make sure this is adjusted for the KSS 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 a best checkpoint is around 150k iters.

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: "fastspeech2"

17


18
fastspeech2_params:

19
    dataset: "kss"

20
    n_speakers: 1

21
    encoder_hidden_size: 384

22
    encoder_num_hidden_layers: 4

23
    encoder_num_attention_heads: 2

24
    encoder_attention_head_size: 192  # hidden_size // num_attention_heads

25
    encoder_intermediate_size: 1024

26
    encoder_intermediate_kernel_size: 3

27
    encoder_hidden_act: "mish"

28
    decoder_hidden_size: 384

29
    decoder_num_hidden_layers: 4

30
    decoder_num_attention_heads: 2

31
    decoder_attention_head_size: 192  # hidden_size // num_attention_heads

32
    decoder_intermediate_size: 1024

33
    decoder_intermediate_kernel_size: 3

34
    decoder_hidden_act: "mish"

35
    variant_prediction_num_conv_layers: 2

36
    variant_predictor_filter: 256

37
    variant_predictor_kernel_size: 3

38
    variant_predictor_dropout_rate: 0.5

39
    num_mels: 80

40
    hidden_dropout_prob: 0.2

41
    attention_probs_dropout_prob: 0.1

42
    max_position_embeddings: 2048

43
    initializer_range: 0.02

44
    output_attentions: False

45
    output_hidden_states: False

46


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

48
#                  DATA LOADER SETTING                    #

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

50
batch_size: 16              # 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
###########################################################

56
#             OPTIMIZER & SCHEDULER SETTING               #

57
###########################################################

58
optimizer_params:

59
    initial_learning_rate: 0.001

60
    end_learning_rate: 0.00005

61
    decay_steps: 150000          # < train_max_steps is recommend.

62
    warmup_proportion: 0.02

63
    weight_decay: 0.001

64


65
gradient_accumulation_steps: 1

66
var_train_expr: null  # trainable variable expr (eg. 'embeddings|encoder|decoder' )

67
                      # must separate by |. if var_train_expr is null then we 

68
                      # training all variable 

69
###########################################################

70
#                    INTERVAL SETTING                     #

71
###########################################################

72
train_max_steps: 200000               # Number of training steps.

73
save_interval_steps: 5000             # Interval steps to save checkpoint.

74
eval_interval_steps: 500              # Interval steps to evaluate the network.

75
log_interval_steps: 200               # Interval steps to record the training log.

76
###########################################################

77
#                     OTHER SETTING                       #

78
###########################################################

79
num_save_intermediate_results: 1  # Number of batch to be saved as intermediate results.

80