From c54bc90d369159342fba5816daa13af7342a2434 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 13 四月 2023 14:22:55 +0800
Subject: [PATCH] Merge pull request #347 from alibaba-damo-academy/dev_cmz
---
funasr/export/models/CT_Transformer.py | 12 ++++++++++--
funasr/models/target_delay_transformer.py | 6 +++++-
funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py | 10 ++++++++++
funasr/export/models/__init__.py | 4 ++--
funasr/models/vad_realtime_transformer.py | 6 +++++-
5 files changed, 32 insertions(+), 6 deletions(-)
diff --git a/funasr/export/models/target_delay_transformer.py b/funasr/export/models/CT_Transformer.py
similarity index 91%
rename from funasr/export/models/target_delay_transformer.py
rename to funasr/export/models/CT_Transformer.py
index 2780d82..ea6ff4f 100644
--- a/funasr/export/models/target_delay_transformer.py
+++ b/funasr/export/models/CT_Transformer.py
@@ -9,7 +9,11 @@
from funasr.export.models.encoder.sanm_encoder import SANMVadEncoder as SANMVadEncoder_export
class CT_Transformer(nn.Module):
-
+ """
+ Author: Speech Lab, Alibaba Group, China
+ CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection
+ https://arxiv.org/pdf/2003.01309.pdf
+ """
def __init__(
self,
model,
@@ -76,7 +80,11 @@
class CT_Transformer_VadRealtime(nn.Module):
-
+ """
+ Author: Speech Lab, Alibaba Group, China
+ CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection
+ https://arxiv.org/pdf/2003.01309.pdf
+ """
def __init__(
self,
model,
diff --git a/funasr/export/models/__init__.py b/funasr/export/models/__init__.py
index f81ff64..0e3a782 100644
--- a/funasr/export/models/__init__.py
+++ b/funasr/export/models/__init__.py
@@ -4,10 +4,10 @@
from funasr.models.e2e_vad import E2EVadModel
from funasr.export.models.e2e_vad import E2EVadModel as E2EVadModel_export
from funasr.models.target_delay_transformer import TargetDelayTransformer
-from funasr.export.models.target_delay_transformer import CT_Transformer as CT_Transformer_export
+from funasr.export.models.CT_Transformer import CT_Transformer as CT_Transformer_export
from funasr.train.abs_model import PunctuationModel
from funasr.models.vad_realtime_transformer import VadRealtimeTransformer
-from funasr.export.models.target_delay_transformer import CT_Transformer_VadRealtime as CT_Transformer_VadRealtime_export
+from funasr.export.models.CT_Transformer import CT_Transformer_VadRealtime as CT_Transformer_VadRealtime_export
def get_model(model, export_config=None):
if isinstance(model, BiCifParaformer):
diff --git a/funasr/models/target_delay_transformer.py b/funasr/models/target_delay_transformer.py
index 84a2e6c..8cd4357 100644
--- a/funasr/models/target_delay_transformer.py
+++ b/funasr/models/target_delay_transformer.py
@@ -13,7 +13,11 @@
class TargetDelayTransformer(AbsPunctuation):
-
+ """
+ Author: Speech Lab, Alibaba Group, China
+ CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection
+ https://arxiv.org/pdf/2003.01309.pdf
+ """
def __init__(
self,
vocab_size: int,
diff --git a/funasr/models/vad_realtime_transformer.py b/funasr/models/vad_realtime_transformer.py
index 66f7fad..3810672 100644
--- a/funasr/models/vad_realtime_transformer.py
+++ b/funasr/models/vad_realtime_transformer.py
@@ -11,7 +11,11 @@
class VadRealtimeTransformer(AbsPunctuation):
-
+ """
+ Author: Speech Lab, Alibaba Group, China
+ CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection
+ https://arxiv.org/pdf/2003.01309.pdf
+ """
def __init__(
self,
vocab_size: int,
diff --git a/funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py b/funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py
index 0eb764f..2f1b3b7 100644
--- a/funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py
+++ b/funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py
@@ -13,6 +13,11 @@
class CT_Transformer():
+ """
+ Author: Speech Lab, Alibaba Group, China
+ CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection
+ https://arxiv.org/pdf/2003.01309.pdf
+ """
def __init__(self, model_dir: Union[str, Path] = None,
batch_size: int = 1,
device_id: Union[str, int] = "-1",
@@ -119,6 +124,11 @@
class CT_Transformer_VadRealtime(CT_Transformer):
+ """
+ Author: Speech Lab, Alibaba Group, China
+ CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection
+ https://arxiv.org/pdf/2003.01309.pdf
+ """
def __init__(self, model_dir: Union[str, Path] = None,
batch_size: int = 1,
device_id: Union[str, int] = "-1",
--
Gitblit v1.9.1