From 219c2482ab755fbd4e49dfbdee91bf1a8a4ec49a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 19 五月 2023 11:33:27 +0800
Subject: [PATCH] websocket 2pass bugfix
---
funasr/models/e2e_asr_transducer.py | 14 +++++++-------
1 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/funasr/models/e2e_asr_transducer.py b/funasr/models/e2e_asr_transducer.py
index f8ba0f0..3120087 100644
--- a/funasr/models/e2e_asr_transducer.py
+++ b/funasr/models/e2e_asr_transducer.py
@@ -12,12 +12,12 @@
from funasr.models.specaug.abs_specaug import AbsSpecAug
from funasr.models.decoder.rnnt_decoder import RNNTDecoder
from funasr.models.decoder.abs_decoder import AbsDecoder as AbsAttDecoder
-from funasr.models.encoder.conformer_encoder import ConformerChunkEncoder as Encoder
+from funasr.models.encoder.abs_encoder import AbsEncoder
from funasr.models.joint_net.joint_network import JointNetwork
from funasr.modules.nets_utils import get_transducer_task_io
from funasr.layers.abs_normalize import AbsNormalize
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 V(torch.__version__) >= V("1.6.0"):
from torch.cuda.amp import autocast
@@ -28,7 +28,7 @@
yield
-class TransducerModel(AbsESPnetModel):
+class TransducerModel(FunASRModel):
"""ESPnet2ASRTransducerModel module definition.
Args:
@@ -62,7 +62,7 @@
frontend: Optional[AbsFrontend],
specaug: Optional[AbsSpecAug],
normalize: Optional[AbsNormalize],
- encoder: Encoder,
+ encoder: AbsEncoder,
decoder: RNNTDecoder,
joint_network: JointNetwork,
att_decoder: Optional[AbsAttDecoder] = None,
@@ -286,7 +286,7 @@
feats, feats_lengths = self.normalize(feats, feats_lengths)
# 4. Forward encoder
- encoder_out, encoder_out_lens = self.encoder(feats, feats_lengths)
+ encoder_out, encoder_out_lens, _ = self.encoder(feats, feats_lengths)
assert encoder_out.size(0) == speech.size(0), (
encoder_out.size(),
@@ -483,7 +483,7 @@
return loss_lm
-class UnifiedTransducerModel(AbsESPnetModel):
+class UnifiedTransducerModel(FunASRModel):
"""ESPnet2ASRTransducerModel module definition.
Args:
vocab_size: Size of complete vocabulary (w/ EOS and blank included).
@@ -515,7 +515,7 @@
frontend: Optional[AbsFrontend],
specaug: Optional[AbsSpecAug],
normalize: Optional[AbsNormalize],
- encoder: Encoder,
+ encoder: AbsEncoder,
decoder: RNNTDecoder,
joint_network: JointNetwork,
att_decoder: Optional[AbsAttDecoder] = None,
--
Gitblit v1.9.1