From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/models/e2e_asr_contextual_paraformer.py | 11 +++++------
1 files changed, 5 insertions(+), 6 deletions(-)
diff --git a/funasr/models/e2e_asr_contextual_paraformer.py b/funasr/models/e2e_asr_contextual_paraformer.py
index dc820db..64e0f8d 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
@@ -343,7 +341,7 @@
input_mask_expand_dim, 0)
return sematic_embeds * tgt_mask, decoder_out * tgt_mask
- def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, hw_list=None):
+ def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, hw_list=None, clas_scale=1.0):
if hw_list is None:
hw_list = [torch.Tensor([1]).long().to(encoder_out.device)] # empty hotword list
hw_list_pad = pad_list(hw_list, 0)
@@ -352,6 +350,7 @@
else:
hw_embed = self.bias_embed(hw_list_pad)
hw_embed, (h_n, _) = self.bias_encoder(hw_embed)
+ hw_embed = h_n.repeat(encoder_out.shape[0], 1, 1)
else:
hw_lengths = [len(i) for i in hw_list]
hw_list_pad = pad_list([torch.Tensor(i).long() for i in hw_list], 0).to(encoder_out.device)
@@ -365,7 +364,7 @@
hw_embed = h_n.repeat(encoder_out.shape[0], 1, 1)
decoder_outs = self.decoder(
- encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=hw_embed
+ encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=hw_embed, clas_scale=clas_scale
)
decoder_out = decoder_outs[0]
decoder_out = torch.log_softmax(decoder_out, dim=-1)
--
Gitblit v1.9.1