From 3e77fd44304a67a2b2253b4e56fede9762bb8464 Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 20 四月 2023 16:41:22 +0800
Subject: [PATCH] update
---
funasr/models/e2e_uni_asr.py | 19 ++++++++-----------
1 files changed, 8 insertions(+), 11 deletions(-)
diff --git a/funasr/models/e2e_uni_asr.py b/funasr/models/e2e_uni_asr.py
index ad6fe41..ee5e2ba 100644
--- a/funasr/models/e2e_uni_asr.py
+++ b/funasr/models/e2e_uni_asr.py
@@ -18,14 +18,11 @@
)
from funasr.models.ctc import CTC
from funasr.models.decoder.abs_decoder import AbsDecoder
-from funasr.models.encoder.abs_encoder import AbsEncoder
-from funasr.models.frontend.abs_frontend import AbsFrontend
from funasr.models.postencoder.abs_postencoder import AbsPostEncoder
from funasr.models.preencoder.abs_preencoder import AbsPreEncoder
-from funasr.models.specaug.abs_specaug import AbsSpecAug
-from funasr.layers.abs_normalize import AbsNormalize
+from funasr.models.base_model import FunASRModel
from funasr.torch_utils.device_funcs import force_gatherable
-from funasr.train.abs_espnet_model import AbsESPnetModel
+from funasr.models.base_model import FunASRModel
from funasr.modules.streaming_utils.chunk_utilis import sequence_mask
from funasr.models.predictor.cif import mae_loss
@@ -38,7 +35,7 @@
yield
-class UniASR(AbsESPnetModel):
+class UniASR(FunASRModel):
"""
Author: Speech Lab, Alibaba Group, China
"""
@@ -47,11 +44,11 @@
self,
vocab_size: int,
token_list: Union[Tuple[str, ...], List[str]],
- frontend: Optional[AbsFrontend],
- specaug: Optional[AbsSpecAug],
- normalize: Optional[AbsNormalize],
+ frontend: Optional[torch.nn.Module],
+ specaug: Optional[torch.nn.Module],
+ normalize: Optional[torch.nn.Module],
preencoder: Optional[AbsPreEncoder],
- encoder: AbsEncoder,
+ encoder: torch.nn.Module,
postencoder: Optional[AbsPostEncoder],
decoder: AbsDecoder,
ctc: CTC,
@@ -206,7 +203,7 @@
with torch.no_grad():
speech_raw, encoder_out, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)
else:
- speech_raw, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)
+ speech_raw, encoder_out, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)
intermediate_outs = None
if isinstance(encoder_out, tuple):
--
Gitblit v1.9.1