-
Notifications
You must be signed in to change notification settings - Fork 3
/
config.yaml
76 lines (60 loc) · 2.53 KB
/
config.yaml
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
### General settings.
## The name of singer
spk: ofikuru
## exp tag(for managing experiments)
tag: jp_qst_crazy_mono_007_enunu_173D
## Output directory
# 学習に使うデータを置く場所。genon_db_dir からここにファイルをコピーしてから学習する。
# All the generated labels, intermediate files, and segmented wav files
# will be saved in the following directory
out_dir: ./data
## Songs to be excluded from trainig.
# NOTE: ここ未実装
exclude_songs: []
## table file for translating lyrics to phonemes.
# NOTE: ラベル作るときに手動指定するので必要ない気がする。
# TODO: 母音と母音の区別をつけるためのconfファイルも使うようにする。
sinsy_dic: ./dic
table_path: ./dic/kana2phonemes_utf8_for_oto2lab_noAIUEO.table
## HTS-style question used for extracting musical/linguistic context from musicxml files
question_path: ./hed/jp_qst_crazy_mono_007_enunu_173D.hed
# Audio sampling rate
# CAUTION: Changing sample_rate may affect the dimension number of acoustic features.
# DO NOT CHANGE this unless you know the relationship between the dim of bap and sample_rate.
sample_rate: 44100
###########################################################
# FEATURE EXTRACTION SETTING #
###########################################################
timelag_features: defaults
duration_features: defaults
acoustic_features: static_deltadelta
###########################################################
# TRAINING SETTING #
###########################################################
# Models
# To customize, put your config or change ones in
# conf/train/{timelag,duration,acoustic}/ and
# specify the config name below
# NOTE: *_model: model definition, *_train: general train configs,
# *_data: data configs (e.g., batch size)
timelag_model: timelag_ffn
timelag_train: myconfig
timelag_data: myconfig
duration_model: duration_lstm
duration_train: myconfig
duration_data: myconfig
acoustic_model: acoustic_conv
acoustic_train: myconfig
acoustic_data: myconfig
# Pretrained model dir (leave empty to disable)
pretrained_expdir:
###########################################################
# SYNTHESIS SETTING #
###########################################################
timelag_synthesis: defaults
duration_synthesis: defaults
acoustic_synthesis: defaults
# latest.pth or best.pth
timelag_eval_checkpoint: best_loss.pth
duration_eval_checkpoint: best_loss.pth
acoustic_eval_checkpoint: best_loss.pth