mirror of
https://github.com/serp-ai/bark-with-voice-clone.git
synced 2025-12-15 19:27:57 +01:00
175 lines
7.1 KiB
Python
175 lines
7.1 KiB
Python
"""
|
|
Much of this code is adapted from Andrej Karpathy's NanoGPT
|
|
(https://github.com/karpathy/nanoGPT)
|
|
"""
|
|
import math
|
|
from dataclasses import dataclass
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
from torch.nn import functional as F
|
|
|
|
class LayerNorm(nn.Module):
|
|
""" LayerNorm but with an optional bias. PyTorch doesn't support simply bias=False """
|
|
|
|
def __init__(self, ndim, bias):
|
|
super().__init__()
|
|
self.weight = nn.Parameter(torch.ones(ndim))
|
|
self.bias = nn.Parameter(torch.zeros(ndim)) if bias else None
|
|
|
|
def forward(self, input):
|
|
return F.layer_norm(input, self.weight.shape, self.weight, self.bias, 1e-5)
|
|
|
|
class CausalSelfAttention(nn.Module):
|
|
|
|
def __init__(self, config):
|
|
super().__init__()
|
|
assert config.n_embd % config.n_head == 0
|
|
# key, query, value projections for all heads, but in a batch
|
|
self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd, bias=config.bias)
|
|
# output projection
|
|
self.c_proj = nn.Linear(config.n_embd, config.n_embd, bias=config.bias)
|
|
# regularization
|
|
self.attn_dropout = nn.Dropout(config.dropout)
|
|
self.resid_dropout = nn.Dropout(config.dropout)
|
|
self.n_head = config.n_head
|
|
self.n_embd = config.n_embd
|
|
self.dropout = config.dropout
|
|
# flash attention make GPU go brrrrr but support is only in PyTorch nightly and still a bit scary
|
|
self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention')
|
|
if not self.flash:
|
|
# print("WARNING: using slow attention. Flash Attention atm needs PyTorch nightly and dropout=0.0")
|
|
# causal mask to ensure that attention is only applied to the left in the input sequence
|
|
self.register_buffer("bias", torch.tril(torch.ones(config.block_size, config.block_size))
|
|
.view(1, 1, config.block_size, config.block_size))
|
|
|
|
def forward(self, x):
|
|
B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
|
|
|
|
# calculate query, key, values for all heads in batch and move head forward to be the batch dim
|
|
q, k ,v = self.c_attn(x).split(self.n_embd, dim=2)
|
|
k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
|
|
q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
|
|
v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
|
|
|
|
# causal self-attention; Self-attend: (B, nh, T, hs) x (B, nh, hs, T) -> (B, nh, T, T)
|
|
if self.flash:
|
|
# efficient attention using Flash Attention CUDA kernels
|
|
y = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=self.dropout, is_causal=True)
|
|
else:
|
|
# manual implementation of attention
|
|
att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
|
|
att = att.masked_fill(self.bias[:,:,:T,:T] == 0, float('-inf'))
|
|
att = F.softmax(att, dim=-1)
|
|
att = self.attn_dropout(att)
|
|
y = att @ v # (B, nh, T, T) x (B, nh, T, hs) -> (B, nh, T, hs)
|
|
y = y.transpose(1, 2).contiguous().view(B, T, C) # re-assemble all head outputs side by side
|
|
|
|
# output projection
|
|
y = self.resid_dropout(self.c_proj(y))
|
|
return y
|
|
|
|
class MLP(nn.Module):
|
|
|
|
def __init__(self, config):
|
|
super().__init__()
|
|
self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd, bias=config.bias)
|
|
self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd, bias=config.bias)
|
|
self.dropout = nn.Dropout(config.dropout)
|
|
self.gelu = nn.GELU()
|
|
|
|
def forward(self, x):
|
|
x = self.c_fc(x)
|
|
x = self.gelu(x)
|
|
x = self.c_proj(x)
|
|
x = self.dropout(x)
|
|
return x
|
|
|
|
class Block(nn.Module):
|
|
|
|
def __init__(self, config, layer_idx):
|
|
super().__init__()
|
|
self.ln_1 = LayerNorm(config.n_embd, bias=config.bias)
|
|
self.attn = CausalSelfAttention(config)
|
|
self.ln_2 = LayerNorm(config.n_embd, bias=config.bias)
|
|
self.mlp = MLP(config)
|
|
self.layer_idx = layer_idx
|
|
|
|
def forward(self, x):
|
|
x = x + self.attn(self.ln_1(x))
|
|
x = x + self.mlp(self.ln_2(x))
|
|
return x
|
|
|
|
@dataclass
|
|
class GPTConfig:
|
|
block_size: int = 1024
|
|
input_vocab_size: int = 10_048
|
|
output_vocab_size: int = 10_048
|
|
n_layer: int = 12
|
|
n_head: int = 12
|
|
n_embd: int = 768
|
|
dropout: float = 0.0
|
|
bias: bool = True # True: bias in Linears and LayerNorms, like GPT-2. False: a bit better and faster
|
|
|
|
class GPT(nn.Module):
|
|
|
|
def __init__(self, config):
|
|
super().__init__()
|
|
assert config.input_vocab_size is not None
|
|
assert config.output_vocab_size is not None
|
|
assert config.block_size is not None
|
|
self.config = config
|
|
|
|
self.transformer = nn.ModuleDict(dict(
|
|
wte = nn.Embedding(config.input_vocab_size, config.n_embd),
|
|
wpe = nn.Embedding(config.block_size, config.n_embd),
|
|
drop = nn.Dropout(config.dropout),
|
|
h = nn.ModuleList([Block(config, idx) for idx in range(config.n_layer)]),
|
|
ln_f = LayerNorm(config.n_embd, bias=config.bias),
|
|
))
|
|
self.lm_head = nn.Linear(config.n_embd, config.output_vocab_size, bias=False)
|
|
|
|
def get_num_params(self, non_embedding=True):
|
|
"""
|
|
Return the number of parameters in the model.
|
|
For non-embedding count (default), the position embeddings get subtracted.
|
|
The token embeddings would too, except due to the parameter sharing these
|
|
params are actually used as weights in the final layer, so we include them.
|
|
"""
|
|
n_params = sum(p.numel() for p in self.parameters())
|
|
if non_embedding:
|
|
n_params -= self.transformer.wte.weight.numel()
|
|
n_params -= self.transformer.wpe.weight.numel()
|
|
return n_params
|
|
|
|
def forward(self, idx, merge_context=False):
|
|
device = idx.device
|
|
b, t = idx.size()
|
|
if merge_context:
|
|
assert(idx.shape[1] >= 256+256+1)
|
|
t = idx.shape[1] - 256
|
|
else:
|
|
assert t <= self.config.block_size, f"Cannot forward sequence of length {t}, block size is only {self.config.block_size}"
|
|
|
|
# forward the GPT model itself
|
|
if merge_context:
|
|
tok_emb = torch.cat([
|
|
self.transformer.wte(idx[:,:256]) + self.transformer.wte(idx[:,256:256+256]),
|
|
self.transformer.wte(idx[:,256+256:])
|
|
], dim=1)
|
|
else:
|
|
tok_emb = self.transformer.wte(idx) # token embeddings of shape (b, t, n_embd)
|
|
|
|
pos = torch.arange(0, t, dtype=torch.long, device=device).unsqueeze(0) # shape (1, t)
|
|
pos_emb = self.transformer.wpe(pos) # position embeddings of shape (1, t, n_embd)
|
|
|
|
x = self.transformer.drop(tok_emb + pos_emb)
|
|
for block in self.transformer.h:
|
|
x = block(x)
|
|
x = self.transformer.ln_f(x)
|
|
|
|
# inference-time mini-optimization: only forward the lm_head on the very last position
|
|
logits = self.lm_head(x[:, [-1], :]) # note: using list [-1] to preserve the time dim
|
|
|
|
return logits
|