From 4e37a5fda20f0878b593b8ba2b9ea46db63743b5 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 11 五月 2023 14:16:28 +0800
Subject: [PATCH] update repo
---
funasr/models/e2e_sv.py | 13 ++++++++-----
1 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/funasr/models/e2e_sv.py b/funasr/models/e2e_sv.py
index eff63d9..bd82c7c 100644
--- a/funasr/models/e2e_sv.py
+++ b/funasr/models/e2e_sv.py
@@ -1,3 +1,8 @@
+
+"""
+Author: Speech Lab, Alibaba Group, China
+"""
+
import logging
from contextlib import contextmanager
from distutils.version import LooseVersion
@@ -25,7 +30,7 @@
from funasr.modules.e2e_asr_common import ErrorCalculator
from funasr.modules.nets_utils import th_accuracy
from funasr.torch_utils.device_funcs import force_gatherable
-from funasr.train.abs_espnet_model import AbsESPnetModel
+from funasr.models.base_model import FunASRModel
if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"):
from torch.cuda.amp import autocast
@@ -36,7 +41,7 @@
yield
-class ESPnetSVModel(AbsESPnetModel):
+class ESPnetSVModel(FunASRModel):
"""CTC-attention hybrid Encoder-Decoder model"""
def __init__(
@@ -76,7 +81,6 @@
text_lengths: torch.Tensor,
) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
"""Frontend + Encoder + Decoder + Calc loss
-
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
@@ -217,7 +221,6 @@
self, speech: torch.Tensor, speech_lengths: torch.Tensor
) -> Tuple[torch.Tensor, torch.Tensor]:
"""Frontend + Encoder. Note that this method is used by asr_inference.py
-
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
@@ -267,4 +270,4 @@
else:
# No frontend and no feature extract
feats, feats_lengths = speech, speech_lengths
- return feats, feats_lengths
+ return feats, feats_lengths
\ No newline at end of file
--
Gitblit v1.9.1