From c542eacb0aadcbc49c63db40429fca4e08f807a4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 21 七月 2023 10:27:35 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/modules/nets_utils.py | 43 ++++++++++++++++++++++++++++++++++---------
1 files changed, 34 insertions(+), 9 deletions(-)
diff --git a/funasr/modules/nets_utils.py b/funasr/modules/nets_utils.py
index 10df124..55c5768 100644
--- a/funasr/modules/nets_utils.py
+++ b/funasr/modules/nets_utils.py
@@ -407,7 +407,7 @@
elif mode == "mt" and arch == "rnn":
# +1 means input (+1) and layers outputs (train_args.elayer)
- subsample = np.ones(train_args.elayers + 1, dtype=np.int)
+ subsample = np.ones(train_args.elayers + 1, dtype=np.int32)
logging.warning("Subsampling is not performed for machine translation.")
logging.info("subsample: " + " ".join([str(x) for x in subsample]))
return subsample
@@ -417,7 +417,7 @@
or (mode == "mt" and arch == "rnn")
or (mode == "st" and arch == "rnn")
):
- subsample = np.ones(train_args.elayers + 1, dtype=np.int)
+ subsample = np.ones(train_args.elayers + 1, dtype=np.int32)
if train_args.etype.endswith("p") and not train_args.etype.startswith("vgg"):
ss = train_args.subsample.split("_")
for j in range(min(train_args.elayers + 1, len(ss))):
@@ -432,7 +432,7 @@
elif mode == "asr" and arch == "rnn_mix":
subsample = np.ones(
- train_args.elayers_sd + train_args.elayers + 1, dtype=np.int
+ train_args.elayers_sd + train_args.elayers + 1, dtype=np.int32
)
if train_args.etype.endswith("p") and not train_args.etype.startswith("vgg"):
ss = train_args.subsample.split("_")
@@ -451,7 +451,7 @@
elif mode == "asr" and arch == "rnn_mulenc":
subsample_list = []
for idx in range(train_args.num_encs):
- subsample = np.ones(train_args.elayers[idx] + 1, dtype=np.int)
+ subsample = np.ones(train_args.elayers[idx] + 1, dtype=np.int32)
if train_args.etype[idx].endswith("p") and not train_args.etype[
idx
].startswith("vgg"):
@@ -485,14 +485,39 @@
new_k = k.replace(old_prefix, new_prefix)
state_dict[new_k] = v
-
class Swish(torch.nn.Module):
- """Construct an Swish object."""
+ """Swish activation definition.
- def forward(self, x):
- """Return Swich activation function."""
- return x * torch.sigmoid(x)
+ Swish(x) = (beta * x) * sigmoid(x)
+ where beta = 1 defines standard Swish activation.
+ References:
+ https://arxiv.org/abs/2108.12943 / https://arxiv.org/abs/1710.05941v1.
+ E-swish variant: https://arxiv.org/abs/1801.07145.
+
+ Args:
+ beta: Beta parameter for E-Swish.
+ (beta >= 1. If beta < 1, use standard Swish).
+ use_builtin: Whether to use PyTorch function if available.
+
+ """
+
+ def __init__(self, beta: float = 1.0, use_builtin: bool = False) -> None:
+ super().__init__()
+
+ self.beta = beta
+
+ if beta > 1:
+ self.swish = lambda x: (self.beta * x) * torch.sigmoid(x)
+ else:
+ if use_builtin:
+ self.swish = torch.nn.SiLU()
+ else:
+ self.swish = lambda x: x * torch.sigmoid(x)
+
+ def forward(self, x: torch.Tensor) -> torch.Tensor:
+ """Forward computation."""
+ return self.swish(x)
def get_activation(act):
"""Return activation function."""
--
Gitblit v1.9.1