From 54931dd4e1a099d7d6f144c4e12e5453deb3aa26 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期三, 28 六月 2023 10:41:57 +0800
Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into main
---
funasr/models/e2e_uni_asr.py | 19 ++++++-------------
1 files changed, 6 insertions(+), 13 deletions(-)
diff --git a/funasr/models/e2e_uni_asr.py b/funasr/models/e2e_uni_asr.py
index ad6fe41..9ec3a39 100644
--- a/funasr/models/e2e_uni_asr.py
+++ b/funasr/models/e2e_uni_asr.py
@@ -25,7 +25,7 @@
from funasr.models.specaug.abs_specaug import AbsSpecAug
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
from funasr.modules.streaming_utils.chunk_utilis import sequence_mask
from funasr.models.predictor.cif import mae_loss
@@ -38,9 +38,9 @@
yield
-class UniASR(AbsESPnetModel):
+class UniASR(FunASRModel):
"""
- Author: Speech Lab, Alibaba Group, China
+ Author: Speech Lab of DAMO Academy, Alibaba Group
"""
def __init__(
@@ -50,9 +50,7 @@
frontend: Optional[AbsFrontend],
specaug: Optional[AbsSpecAug],
normalize: Optional[AbsNormalize],
- preencoder: Optional[AbsPreEncoder],
encoder: AbsEncoder,
- postencoder: Optional[AbsPostEncoder],
decoder: AbsDecoder,
ctc: CTC,
ctc_weight: float = 0.5,
@@ -80,6 +78,8 @@
loss_weight_model1: float = 0.5,
enable_maas_finetune: bool = False,
freeze_encoder2: bool = False,
+ preencoder: Optional[AbsPreEncoder] = None,
+ postencoder: Optional[AbsPostEncoder] = None,
encoder1_encoder2_joint_training: bool = True,
):
assert check_argument_types()
@@ -179,7 +179,6 @@
decoding_ind: int = None,
) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
"""Frontend + Encoder + Decoder + Calc loss
-
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
@@ -206,7 +205,7 @@
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):
@@ -469,7 +468,6 @@
self, speech: torch.Tensor, speech_lengths: torch.Tensor, ind: int = 0,
) -> Tuple[torch.Tensor, torch.Tensor]:
"""Frontend + Encoder. Note that this method is used by asr_inference.py
-
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
@@ -533,7 +531,6 @@
ind: int = 0,
) -> Tuple[torch.Tensor, torch.Tensor]:
"""Frontend + Encoder. Note that this method is used by asr_inference.py
-
Args:
speech: (Batch, Length, ...)
speech_lengths: (Batch, )
@@ -627,9 +624,7 @@
ys_pad_lens: torch.Tensor,
) -> torch.Tensor:
"""Compute negative log likelihood(nll) from transformer-decoder
-
Normally, this function is called in batchify_nll.
-
Args:
encoder_out: (Batch, Length, Dim)
encoder_out_lens: (Batch,)
@@ -666,7 +661,6 @@
batch_size: int = 100,
):
"""Compute negative log likelihood(nll) from transformer-decoder
-
To avoid OOM, this fuction seperate the input into batches.
Then call nll for each batch and combine and return results.
Args:
@@ -1072,4 +1066,3 @@
ys_hat = self.ctc2.argmax(encoder_out).data
cer_ctc = self.error_calculator(ys_hat.cpu(), ys_pad.cpu(), is_ctc=True)
return loss_ctc, cer_ctc
-
--
Gitblit v1.9.1