Spaces:
Running
on
Zero
Running
on
Zero
File size: 9,711 Bytes
20a29ac |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 |
""" VibeVoice_AcousticTokenizer model configuration"""
from typing import Dict, List, Optional, Tuple
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
from transformers.models.qwen2.configuration_qwen2 import Qwen2Config
logger = logging.get_logger(__name__)
class VibeVoiceAcousticTokenizerConfig(PretrainedConfig):
model_type = "vibevoice_acoustic_tokenizer"
def __init__(
self,
channels: int = 1,
corpus_normalize: float = 0.0,
causal: bool = True,
vae_dim: int = 64,
fix_std: float = 0.5,
std_dist_type: str = 'gaussian',
# common
mixer_layer: str = 'depthwise_conv',
conv_norm: str = 'none',
pad_mode: str = 'constant',
disable_last_norm: bool = True,
layernorm: str = 'RMSNorm',
layernorm_eps: float = 1e-5,
layernorm_elementwise_affine: bool = True,
conv_bias: bool = True,
layer_scale_init_value: float = 1e-6,
weight_init_value: float = 1e-2,
# encoder specific
encoder_n_filters: int = 32,
encoder_ratios: Optional[List[int]] = [8,5,5,4,2,2],
encoder_depths: str = "3-3-3-3-3-3-8",
# decoder specific
decoder_n_filters: int = 32,
decoder_ratios: Optional[List[int]] = None, # if None, same as encoder
decoder_depths: Optional[str] = None,
**kwargs
):
super().__init__(**kwargs)
self.channels = channels
self.corpus_normalize = corpus_normalize
self.causal = causal
self.vae_dim = vae_dim
self.fix_std = fix_std
self.std_dist_type = std_dist_type
# common parameters
self.conv_norm = conv_norm
self.pad_mode = pad_mode
self.layernorm_eps = layernorm_eps
self.disable_last_norm = disable_last_norm
self.layernorm = layernorm
self.layernorm_elementwise_affine = layernorm_elementwise_affine
self.conv_bias = conv_bias
self.layer_scale_init_value = layer_scale_init_value
self.weight_init_value = weight_init_value
self.mixer_layer = mixer_layer
# encoder specific parameters
self.encoder_n_filters = encoder_n_filters
self.encoder_ratios = encoder_ratios
self.encoder_depths = encoder_depths
# decoder specific parameters
self.decoder_ratios = decoder_ratios if decoder_ratios is not None else encoder_ratios
self.decoder_n_filters = decoder_n_filters
self.decoder_depths = decoder_depths
class VibeVoiceSemanticTokenizerConfig(PretrainedConfig):
model_type = "vibevoice_semantic_tokenizer"
def __init__(
self,
channels: int = 1,
corpus_normalize: float = 0.0,
causal: bool = True,
vae_dim: int = 64,
fix_std: float = 0,
std_dist_type: str = 'none',
# common
mixer_layer: str = 'depthwise_conv',
conv_norm: str = 'none',
pad_mode: str = 'constant',
disable_last_norm: bool = True,
layernorm: str = 'RMSNorm',
layernorm_eps: float = 1e-5,
layernorm_elementwise_affine: bool = True,
conv_bias: bool = True,
layer_scale_init_value: float = 1e-6,
weight_init_value: float = 1e-2,
# encoder specific
encoder_n_filters: int = 32,
encoder_ratios: Optional[List[int]] = [8,5,5,4,2,2],
encoder_depths: str = "3-3-3-3-3-3-8",
**kwargs
):
super().__init__(**kwargs)
self.channels = channels
self.corpus_normalize = corpus_normalize
self.causal = causal
self.vae_dim = vae_dim
self.fix_std = fix_std
self.std_dist_type = std_dist_type
# common parameters
self.conv_norm = conv_norm
self.pad_mode = pad_mode
self.layernorm_eps = layernorm_eps
self.disable_last_norm = disable_last_norm
self.layernorm = layernorm
self.layernorm_elementwise_affine = layernorm_elementwise_affine
self.conv_bias = conv_bias
self.layer_scale_init_value = layer_scale_init_value
self.weight_init_value = weight_init_value
self.mixer_layer = mixer_layer
# encoder specific parameters
self.encoder_n_filters = encoder_n_filters
self.encoder_ratios = encoder_ratios
self.encoder_depths = encoder_depths
class VibeVoiceDiffusionHeadConfig(PretrainedConfig):
model_type = "vibevoice_diffusion_head"
def __init__(
self,
hidden_size=768,
head_layers=4,
head_ffn_ratio=3.0,
rms_norm_eps=1e-5,
latent_size=64,
speech_vae_dim=None,
prediction_type="v_prediction",
diffusion_type="ddpm",
ddpm_num_steps=1000,
ddpm_num_inference_steps=20,
ddpm_beta_schedule="cosine",
ddpm_batch_mul=4,
**kwargs
):
self.hidden_size = hidden_size
self.head_layers = head_layers
self.head_ffn_ratio = head_ffn_ratio
self.rms_norm_eps = rms_norm_eps
self.latent_size = latent_size
self.speech_vae_dim = speech_vae_dim
self.prediction_type = prediction_type
self.diffusion_type = diffusion_type
self.ddpm_num_steps = ddpm_num_steps
self.ddpm_num_inference_steps = ddpm_num_inference_steps
self.ddpm_beta_schedule = ddpm_beta_schedule
self.ddpm_batch_mul = ddpm_batch_mul
super().__init__(**kwargs)
class VibeVoiceConfig(PretrainedConfig):
model_type = "vibevoice"
is_composition = True
sub_configs = {
"acoustic_tokenizer_config": VibeVoiceAcousticTokenizerConfig,
"semantic_tokenizer_config": VibeVoiceSemanticTokenizerConfig,
"decoder_config": Qwen2Config,
"diffusion_head_config": VibeVoiceDiffusionHeadConfig,
}
# keys_to_ignore_at_inference = ["past_key_values"]
# Default tensor parallel plan for base model `Qwen2`
base_model_tp_plan = {
"layers.*.self_attn.q_proj": "colwise",
"layers.*.self_attn.k_proj": "colwise",
"layers.*.self_attn.v_proj": "colwise",
"layers.*.self_attn.o_proj": "rowwise",
"layers.*.mlp.gate_proj": "colwise",
"layers.*.mlp.up_proj": "colwise",
"layers.*.mlp.down_proj": "rowwise",
}
def __init__(
self,
acoustic_tokenizer_config=None,
semantic_tokenizer_config=None,
decoder_config=None,
diffusion_head_config=None,
**kwargs
):
# kwargs["_attn_implementation"] = "flash_attention_2"
kwargs["_attn_implementation_autoset"] = False
if acoustic_tokenizer_config is None:
self.acoustic_tokenizer_config = self.sub_configs["acoustic_tokenizer_config"]()
elif isinstance(acoustic_tokenizer_config, dict):
acoustic_tokenizer_config["model_type"] = "vibevoice_acoustic_tokenizer"
self.acoustic_tokenizer_config = self.sub_configs["acoustic_tokenizer_config"](**acoustic_tokenizer_config)
elif isinstance(acoustic_tokenizer_config, VibeVoiceAcousticTokenizerConfig):
# If an instance of the config class is provided
self.acoustic_tokenizer_config = acoustic_tokenizer_config
if semantic_tokenizer_config is None:
self.semantic_tokenizer_config = self.sub_configs["semantic_tokenizer_config"]()
elif isinstance(semantic_tokenizer_config, dict):
semantic_tokenizer_config["model_type"] = "vibevoice_semantic_tokenizer"
self.semantic_tokenizer_config = self.sub_configs["semantic_tokenizer_config"](**semantic_tokenizer_config)
elif isinstance(semantic_tokenizer_config, VibeVoiceSemanticTokenizerConfig):
# If an instance of the config class is provided
self.semantic_tokenizer_config = semantic_tokenizer_config
if decoder_config is None:
self.decoder_config = self.sub_configs["decoder_config"]()
elif isinstance(decoder_config, dict):
# If a dictionary is provided, instantiate the config class with it
# self.decoder_config = self.sub_configs["decoder_config"](**decoder_config)
if decoder_config.get("model_type", '') == "qwen2":
self.decoder_config = Qwen2Config(**decoder_config)
else:
raise ValueError(f"Unsupported decoder model type: {decoder_config.get('model_type', '')}")
elif isinstance(decoder_config, (Qwen2Config,)):
# If an instance of the config class is provided
self.decoder_config = decoder_config
if diffusion_head_config is None:
self.diffusion_head_config = self.sub_configs["diffusion_head_config"]()
elif isinstance(diffusion_head_config, dict):
diffusion_head_config["model_type"] = "vibevoice_diffusion_head"
self.diffusion_head_config = self.sub_configs["diffusion_head_config"](**diffusion_head_config)
elif isinstance(diffusion_head_config, VibeVoiceDiffusionHeadConfig):
# If an instance of the config class is provided
self.diffusion_head_config = diffusion_head_config
# other parameters
self.acoustic_vae_dim = getattr(self.acoustic_tokenizer_config, 'vae_dim', 64)
self.semantic_vae_dim = getattr(self.semantic_tokenizer_config, 'vae_dim', 128)
super().__init__(**kwargs)
__all__ = [
"VibeVoiceAcousticTokenizerConfig",
"VibeVoiceSemanticTokenizerConfig",
"VibeVoiceDiffusionHeadConfig",
"VibeVoiceConfig"
] |