From 729ac44000a5c4aa23dcb1a3b80adc119a350b23 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 15 三月 2023 19:10:16 +0800
Subject: [PATCH] Merge pull request #235 from alibaba-damo-academy/dev_wjm
---
funasr/modules/eend_ola/encoder_decoder_attractor.py | 6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/funasr/modules/eend_ola/encoder_decoder_attractor.py b/funasr/modules/eend_ola/encoder_decoder_attractor.py
index db01b00..45ac982 100644
--- a/funasr/modules/eend_ola/encoder_decoder_attractor.py
+++ b/funasr/modules/eend_ola/encoder_decoder_attractor.py
@@ -16,12 +16,12 @@
self.n_units = n_units
def forward_core(self, xs, zeros):
- ilens = torch.from_numpy(np.array([x.shape[0] for x in xs])).to(torch.float32).to(xs[0].device)
+ ilens = torch.from_numpy(np.array([x.shape[0] for x in xs])).to(torch.int64)
xs = [self.enc0_dropout(x) for x in xs]
xs = nn.utils.rnn.pad_sequence(xs, batch_first=True, padding_value=-1)
xs = nn.utils.rnn.pack_padded_sequence(xs, ilens, batch_first=True, enforce_sorted=False)
_, (hx, cx) = self.encoder(xs)
- zlens = torch.from_numpy(np.array([z.shape[0] for z in zeros])).to(torch.float32).to(zeros[0].device)
+ zlens = torch.from_numpy(np.array([z.shape[0] for z in zeros])).to(torch.int64)
max_zlen = torch.max(zlens).to(torch.int).item()
zeros = [self.enc0_dropout(z) for z in zeros]
zeros = nn.utils.rnn.pad_sequence(zeros, batch_first=True, padding_value=-1)
@@ -47,4 +47,4 @@
zeros = [torch.zeros(max_n_speakers, self.n_units).to(torch.float32).to(xs[0].device) for _ in xs]
attractors = self.forward_core(xs, zeros)
probs = [torch.sigmoid(torch.flatten(self.counter(att))) for att in attractors]
- return attractors, probs
\ No newline at end of file
+ return attractors, probs
--
Gitblit v1.9.1