From 6be2975020ad3524fed585f519ae6d11f02eae4e Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期一, 08 一月 2024 16:51:27 +0800
Subject: [PATCH] json stamp_sents
---
funasr/models/e2e_asr_contextual_paraformer.py | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/funasr/models/e2e_asr_contextual_paraformer.py b/funasr/models/e2e_asr_contextual_paraformer.py
index 171a6c6..b474dbc 100644
--- a/funasr/models/e2e_asr_contextual_paraformer.py
+++ b/funasr/models/e2e_asr_contextual_paraformer.py
@@ -125,6 +125,7 @@
if self.crit_attn_weight > 0:
self.attn_loss = torch.nn.L1Loss()
self.crit_attn_smooth = crit_attn_smooth
+ self.length_normalized_loss = length_normalized_loss
def forward(
self,
@@ -207,7 +208,7 @@
# 2b. Attention decoder branch
if self.ctc_weight != 1.0:
loss_att, acc_att, cer_att, wer_att, loss_pre, loss_ideal = self._calc_att_clas_loss(
- encoder_out, encoder_out_lens, text, text_lengths, hotword_pad, hotword_lengths, ideal_attn
+ encoder_out, encoder_out_lens, text, text_lengths, hotword_pad, hotword_lengths
)
# 3. CTC-Att loss definition
@@ -231,6 +232,8 @@
stats["loss"] = torch.clone(loss.detach())
# force_gatherable: to-device and to-tensor if scalar for DataParallel
+ if self.length_normalized_loss:
+ batch_size = int((text_lengths + self.predictor_bias).sum())
loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
return loss, stats, weight
@@ -242,7 +245,6 @@
ys_pad_lens: torch.Tensor,
hotword_pad: torch.Tensor,
hotword_lengths: torch.Tensor,
- ideal_attn: torch.Tensor,
):
encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(
encoder_out.device)
--
Gitblit v1.9.1