Spaces:
Runtime error
Runtime error
File size: 7,198 Bytes
9b2107c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 |
from dataclasses import dataclass, field
from typing import List
from TTS.tts.configs.shared_configs import BaseTTSConfig
from TTS.tts.models.forward_tts import ForwardTTSArgs
@dataclass
class SpeedySpeechConfig(BaseTTSConfig):
"""Configure `ForwardTTS` as SpeedySpeech model.
Example:
>>> from TTS.tts.configs.speedy_speech_config import SpeedySpeechConfig
>>> config = SpeedySpeechConfig()
Args:
model (str):
Model name used for selecting the right model at initialization. Defaults to `speedy_speech`.
base_model (str):
Name of the base model being configured as this model so that 🐸 TTS knows it needs to initiate
the base model rather than searching for the `model` implementation. Defaults to `forward_tts`.
model_args (Coqpit):
Model class arguments. Check `FastPitchArgs` for more details. Defaults to `FastPitchArgs()`.
data_dep_init_steps (int):
Number of steps used for computing normalization parameters at the beginning of the training. GlowTTS uses
Activation Normalization that pre-computes normalization stats at the beginning and use the same values
for the rest. Defaults to 10.
speakers_file (str):
Path to the file containing the list of speakers. Needed at inference for loading matching speaker ids to
speaker names. Defaults to `None`.
use_speaker_embedding (bool):
enable / disable using speaker embeddings for multi-speaker models. If set True, the model is
in the multi-speaker mode. Defaults to False.
use_d_vector_file (bool):
enable /disable using external speaker embeddings in place of the learned embeddings. Defaults to False.
d_vector_file (str):
Path to the file including pre-computed speaker embeddings. Defaults to None.
d_vector_dim (int):
Dimension of the external speaker embeddings. Defaults to 0.
optimizer (str):
Name of the model optimizer. Defaults to `RAdam`.
optimizer_params (dict):
Arguments of the model optimizer. Defaults to `{"betas": [0.9, 0.998], "weight_decay": 1e-6}`.
lr_scheduler (str):
Name of the learning rate scheduler. Defaults to `Noam`.
lr_scheduler_params (dict):
Arguments of the learning rate scheduler. Defaults to `{"warmup_steps": 4000}`.
lr (float):
Initial learning rate. Defaults to `1e-3`.
grad_clip (float):
Gradient norm clipping value. Defaults to `5.0`.
spec_loss_type (str):
Type of the spectrogram loss. Check `ForwardTTSLoss` for possible values. Defaults to `l1`.
duration_loss_type (str):
Type of the duration loss. Check `ForwardTTSLoss` for possible values. Defaults to `huber`.
use_ssim_loss (bool):
Enable/disable the use of SSIM (Structural Similarity) loss. Defaults to True.
wd (float):
Weight decay coefficient. Defaults to `1e-7`.
ssim_loss_alpha (float):
Weight for the SSIM loss. If set 0, disables the SSIM loss. Defaults to 1.0.
dur_loss_alpha (float):
Weight for the duration predictor's loss. If set 0, disables the huber loss. Defaults to 1.0.
spec_loss_alpha (float):
Weight for the L1 spectrogram loss. If set 0, disables the L1 loss. Defaults to 1.0.
binary_loss_alpha (float):
Weight for the binary loss. If set 0, disables the binary loss. Defaults to 1.0.
binary_loss_warmup_epochs (float):
Number of epochs to gradually increase the binary loss impact. Defaults to 150.
min_seq_len (int):
Minimum input sequence length to be used at training.
max_seq_len (int):
Maximum input sequence length to be used at training. Larger values result in more VRAM usage.
"""
model: str = "speedy_speech"
base_model: str = "forward_tts"
# set model args as SpeedySpeech
model_args: ForwardTTSArgs = field(
default_factory=lambda: ForwardTTSArgs(
use_pitch=False,
encoder_type="residual_conv_bn",
encoder_params={
"kernel_size": 4,
"dilations": 4 * [1, 2, 4] + [1],
"num_conv_blocks": 2,
"num_res_blocks": 13,
},
decoder_type="residual_conv_bn",
decoder_params={
"kernel_size": 4,
"dilations": 4 * [1, 2, 4, 8] + [1],
"num_conv_blocks": 2,
"num_res_blocks": 17,
},
out_channels=80,
hidden_channels=128,
positional_encoding=True,
detach_duration_predictor=True,
)
)
# multi-speaker settings
num_speakers: int = 0
speakers_file: str = None
use_speaker_embedding: bool = False
use_d_vector_file: bool = False
d_vector_file: str = False
d_vector_dim: int = 0
# optimizer parameters
optimizer: str = "Adam"
optimizer_params: dict = field(default_factory=lambda: {"betas": [0.9, 0.998], "weight_decay": 1e-6})
lr_scheduler: str = "NoamLR"
lr_scheduler_params: dict = field(default_factory=lambda: {"warmup_steps": 4000})
lr: float = 1e-4
grad_clip: float = 5.0
# loss params
spec_loss_type: str = "l1"
duration_loss_type: str = "huber"
use_ssim_loss: bool = False
ssim_loss_alpha: float = 1.0
dur_loss_alpha: float = 1.0
spec_loss_alpha: float = 1.0
aligner_loss_alpha: float = 1.0
binary_align_loss_alpha: float = 0.3
binary_loss_warmup_epochs: int = 150
# overrides
min_seq_len: int = 13
max_seq_len: int = 200
r: int = 1 # DO NOT CHANGE
# dataset configs
compute_f0: bool = False
f0_cache_path: str = None
# testing
test_sentences: List[str] = field(
default_factory=lambda: [
"It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
"Be a voice, not an echo.",
"I'm sorry Dave. I'm afraid I can't do that.",
"This cake is great. It's so delicious and moist.",
"Prior to November 22, 1963.",
]
)
def __post_init__(self):
# Pass multi-speaker parameters to the model args as `model.init_multispeaker()` looks for it there.
if self.num_speakers > 0:
self.model_args.num_speakers = self.num_speakers
# speaker embedding settings
if self.use_speaker_embedding:
self.model_args.use_speaker_embedding = True
if self.speakers_file:
self.model_args.speakers_file = self.speakers_file
# d-vector settings
if self.use_d_vector_file:
self.model_args.use_d_vector_file = True
if self.d_vector_dim is not None and self.d_vector_dim > 0:
self.model_args.d_vector_dim = self.d_vector_dim
if self.d_vector_file:
self.model_args.d_vector_file = self.d_vector_file
|