Commit
•
1ed2cd9
1
Parent(s):
1db491d
🖤 Update config, processor and checkpoint for Tacotron2 Thorsten German.
Browse files- config.yml +86 -0
- model.h5 +3 -0
- processor.json +1 -0
config.yml
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This is the hyperparameter configuration file for Tacotron2 v1.
|
2 |
+
# Please make sure this is adjusted for the Thorsten 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: thorsten
|
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.
|
model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afcbb68abd2d3b74b32ffc5ed645362c6aec68b4b761a822b6379b69c0caf4b2
|
3 |
+
size 127989712
|
processor.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"symbol_to_id": {"pad": 0, "-": 1, "!": 2, "'": 3, "(": 4, ")": 5, ",": 6, ".": 7, "?": 8, " ": 9, "A": 10, "B": 11, "C": 12, "D": 13, "E": 14, "F": 15, "G": 16, "H": 17, "I": 18, "J": 19, "K": 20, "L": 21, "M": 22, "N": 23, "O": 24, "P": 25, "Q": 26, "R": 27, "S": 28, "T": 29, "U": 30, "V": 31, "W": 32, "X": 33, "Y": 34, "Z": 35, "a": 36, "b": 37, "c": 38, "d": 39, "e": 40, "f": 41, "g": 42, "h": 43, "i": 44, "j": 45, "k": 46, "l": 47, "m": 48, "n": 49, "o": 50, "p": 51, "q": 52, "r": 53, "s": 54, "t": 55, "u": 56, "v": 57, "w": 58, "x": 59, "y": 60, "z": 61, "eos": 62}, "id_to_symbol": {"0": "pad", "1": "-", "2": "!", "3": "'", "4": "(", "5": ")", "6": ",", "7": ".", "8": "?", "9": " ", "10": "A", "11": "B", "12": "C", "13": "D", "14": "E", "15": "F", "16": "G", "17": "H", "18": "I", "19": "J", "20": "K", "21": "L", "22": "M", "23": "N", "24": "O", "25": "P", "26": "Q", "27": "R", "28": "S", "29": "T", "30": "U", "31": "V", "32": "W", "33": "X", "34": "Y", "35": "Z", "36": "a", "37": "b", "38": "c", "39": "d", "40": "e", "41": "f", "42": "g", "43": "h", "44": "i", "45": "j", "46": "k", "47": "l", "48": "m", "49": "n", "50": "o", "51": "p", "52": "q", "53": "r", "54": "s", "55": "t", "56": "u", "57": "v", "58": "w", "59": "x", "60": "y", "61": "z", "62": "eos"}, "speakers_map": {"thorsten": 0}, "processor_name": "ThorstenProcessor"}
|