From c798a0c7bb48d2ae5cc5502c8c283bbbb4cdbf8e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 29 六月 2023 20:00:02 +0800
Subject: [PATCH] export
---
funasr/models/e2e_asr_contextual_paraformer.py | 33 +++------------------------------
1 files changed, 3 insertions(+), 30 deletions(-)
diff --git a/funasr/models/e2e_asr_contextual_paraformer.py b/funasr/models/e2e_asr_contextual_paraformer.py
index aced11e..4836663 100644
--- a/funasr/models/e2e_asr_contextual_paraformer.py
+++ b/funasr/models/e2e_asr_contextual_paraformer.py
@@ -9,7 +9,6 @@
import numpy as np
import torch
-from typeguard import check_argument_types
from funasr.layers.abs_normalize import AbsNormalize
from funasr.models.ctc import CTC
@@ -43,9 +42,7 @@
frontend: Optional[AbsFrontend],
specaug: Optional[AbsSpecAug],
normalize: Optional[AbsNormalize],
- preencoder: Optional[AbsPreEncoder],
encoder: AbsEncoder,
- postencoder: Optional[AbsPostEncoder],
decoder: AbsDecoder,
ctc: CTC,
ctc_weight: float = 0.5,
@@ -72,8 +69,9 @@
crit_attn_weight: float = 0.0,
crit_attn_smooth: float = 0.0,
bias_encoder_dropout_rate: float = 0.0,
+ preencoder: Optional[AbsPreEncoder] = None,
+ postencoder: Optional[AbsPostEncoder] = None,
):
- assert check_argument_types()
assert 0.0 <= ctc_weight <= 1.0, ctc_weight
assert 0.0 <= interctc_weight < 1.0, interctc_weight
@@ -291,7 +289,7 @@
loss_ideal = None
'''
loss_ideal = None
-
+
if decoder_out_1st is None:
decoder_out_1st = decoder_out
# 2. Compute attention loss
@@ -362,11 +360,6 @@
hw_embed = torch.nn.utils.rnn.pack_padded_sequence(hw_embed, hw_lengths, batch_first=True,
enforce_sorted=False)
_, (h_n, _) = self.bias_encoder(hw_embed)
- # hw_embed, _ = torch.nn.utils.rnn.pad_packed_sequence(hw_embed, batch_first=True)
- if h_n.shape[1] > 2000: # large hotword list
- _h_n = self.pick_hwlist_group(h_n.squeeze(0), encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens)
- if _h_n is not None:
- h_n = _h_n
hw_embed = h_n.repeat(encoder_out.shape[0], 1, 1)
decoder_outs = self.decoder(
@@ -375,23 +368,3 @@
decoder_out = decoder_outs[0]
decoder_out = torch.log_softmax(decoder_out, dim=-1)
return decoder_out, ys_pad_lens
-
- def pick_hwlist_group(self, hw_embed, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens):
- max_attn_score = 0.0
- # max_attn_index = 0
- argmax_g = None
- non_blank = hw_embed[-1]
- hw_embed_groups = hw_embed[:-1].split(2000)
- for i, g in enumerate(hw_embed_groups):
- g = torch.cat([g, non_blank.unsqueeze(0)], dim=0)
- _ = self.decoder(
- encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=g.unsqueeze(0)
- )
- attn = self.decoder.bias_decoder.src_attn.attn[0]
- _max_attn_score = attn.max(0)[0][:,:-1].max()
- if _max_attn_score > max_attn_score:
- max_attn_score = _max_attn_score
- # max_attn_index = i
- argmax_g = g
- # import pdb; pdb.set_trace()
- return argmax_g
\ No newline at end of file
--
Gitblit v1.9.1