From d5a80d642a5721eb1352cba59833a5cf4b91000f Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 11 四月 2023 00:09:29 +0800
Subject: [PATCH] update
---
funasr/models/e2e_tp.py | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/funasr/models/e2e_tp.py b/funasr/models/e2e_tp.py
index 9850051..ac8c3b4 100644
--- a/funasr/models/e2e_tp.py
+++ b/funasr/models/e2e_tp.py
@@ -14,10 +14,10 @@
from funasr.models.encoder.abs_encoder import AbsEncoder
from funasr.models.frontend.abs_frontend import AbsFrontend
from funasr.models.predictor.cif import mae_loss
+from funasr.models.base_model import FunASRModel
from funasr.modules.add_sos_eos import add_sos_eos
from funasr.modules.nets_utils import make_pad_mask, pad_list
from funasr.torch_utils.device_funcs import force_gatherable
-from funasr.train.abs_espnet_model import AbsESPnetModel
from funasr.models.predictor.cif import CifPredictorV3
@@ -30,7 +30,7 @@
yield
-class TimestampPredictor(AbsESPnetModel):
+class TimestampPredictor(FunASRModel):
"""
Author: Speech Lab, Alibaba Group, China
"""
@@ -150,10 +150,10 @@
def calc_predictor_timestamp(self, encoder_out, encoder_out_lens, token_num):
encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(
encoder_out.device)
- ds_alphas, ds_cif_peak, us_alphas, us_cif_peak = self.predictor.get_upsample_timestamp(encoder_out,
+ ds_alphas, ds_cif_peak, us_alphas, us_peaks = self.predictor.get_upsample_timestamp(encoder_out,
encoder_out_mask,
token_num)
- return ds_alphas, ds_cif_peak, us_alphas, us_cif_peak
+ return ds_alphas, ds_cif_peak, us_alphas, us_peaks
def collect_feats(
self,
--
Gitblit v1.9.1