Hugging Face's logo

SamPurkis
/
data-soong-voice-medium-cleaned-55-samples

Transformers
Inference Endpoints
Model card Files Community
data-soong-voice-medium-cleaned-55-samples
File size: 2,413 Bytes 
9c03593
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5174d75
9c03593
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
128
129
130
131
132
133
 
accelerator: gpu
accumulate_grad_batches: null
amp_backend: native
amp_level: null
auto_lr_find: false
auto_scale_batch_size: false
auto_select_gpus: false
batch_size: 4
benchmark: null
betas: !!python/tuple
- 0.8
- 0.99
c_kl: 1.0
c_mel: 45
channels: 1
check_val_every_n_epoch: 1
checkpoint_epochs: 1
dataset:
- !!python/object/apply:pathlib.PosixPath
  - /
  - kaggle
  - working
  - piper
  - Test-high-cleaned-210-samples
  - dataset.jsonl
dataset_dir: &id001 !!python/object/apply:pathlib.PosixPath
- /
- kaggle
- working
- piper
- Test-high-cleaned-210-samples
default_root_dir: *id001
detect_anomaly: false
deterministic: null
devices: '1'
enable_checkpointing: true
enable_model_summary: true
enable_progress_bar: true
eps: 1.0e-09
fast_dev_run: false
filter_channels: 768
filter_length: 1024
gin_channels: 0
gpus: null
grad_clip: null
gradient_clip_algorithm: null
gradient_clip_val: null
hidden_channels: 192
hop_length: 256
init_lr_ratio: 1.0
inter_channels: 192
ipus: null
kernel_size: 3
learning_rate: 0.0002
limit_predict_batches: null
limit_test_batches: null
limit_train_batches: null
limit_val_batches: null
log_every_n_steps: 10
logger: true
lr_decay: 0.999875
max_epochs: 200
max_phoneme_ids: null
max_steps: -1
max_time: null
mel_channels: 80
mel_fmax: null
mel_fmin: 0.0
min_epochs: null
min_steps: null
move_metrics_to_cpu: false
multiple_trainloader_mode: max_size_cycle
n_heads: 2
n_layers: 6
n_layers_q: 3
num_ckpt: 0
num_nodes: 1
num_processes: null
num_sanity_val_steps: 2
num_speakers: 2
num_symbols: 256
num_test_examples: 0
num_workers: 1
overfit_batches: 0.0
p_dropout: 0.1
plugins: null
precision: 32
profiler: null
quality: high
reload_dataloaders_every_n_epochs: 0
replace_sampler_ddp: true
resblock: '1'
resblock_dilation_sizes: !!python/tuple
- &id002 !!python/tuple
  - 1
  - 3
  - 5
- *id002
- *id002
resblock_kernel_sizes: !!python/tuple
- 3
- 7
- 11
resume_from_checkpoint: null
resume_from_single_speaker_checkpoint: /content/pretrained.ckpt
sample_bytes: 2
sample_rate: 22050
save_last: true
seed: 1234
segment_size: 8192
strategy: null
sync_batchnorm: false
tpu_cores: null
track_grad_norm: -1
upsample_initial_channel: 512
upsample_kernel_sizes: !!python/tuple
- 16
- 16
- 4
- 4
upsample_rates: !!python/tuple
- 8
- 8
- 2
- 2
use_sdp: true
use_spectral_norm: false
val_check_interval: null
validation_split: 0.0
warmup_epochs: 0
weights_save_path: null
win_length: 1024