From fddb28f026f7eddd1a23341253256e96cfa0328c Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 27 十二月 2023 23:05:49 +0800
Subject: [PATCH] Merge branch 'dev_gzf_funasr2' of github.com:alibaba-damo-academy/FunASR into dev_gzf_funasr2 add
---
/dev/null | 12 ------------
funasr/models/contextual_paraformer/__init__.py | 0
examples/industrial_data_pretraining/contextual_paraformer/infer.sh | 2 +-
funasr/models/contextual_paraformer/model.py | 8 ++++----
examples/industrial_data_pretraining/contextual_paraformer/demo.py | 12 ++++++++++++
funasr/models/contextual_paraformer/template.yaml | 2 +-
examples/industrial_data_pretraining/seaco_paraformer/infer.sh | 4 ++--
funasr/models/contextual_paraformer/decoder.py | 0
examples/industrial_data_pretraining/seaco_paraformer/demo.py | 12 ++++++++++++
9 files changed, 32 insertions(+), 20 deletions(-)
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/demo.py b/examples/industrial_data_pretraining/contextual_paraformer/demo.py
new file mode 100644
index 0000000..0edbb2a
--- /dev/null
+++ b/examples/industrial_data_pretraining/contextual_paraformer/demo.py
@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+# -*- encoding: utf-8 -*-
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
+from funasr import AutoModel
+
+model = AutoModel(model="../modelscope_models/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404")
+
+res = model(input="../modelscope_models/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/example/asr_example.wav",
+ hotword='杈鹃瓟闄� 榄旀惌')
+print(res)
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/neat_contextual_paraformer/infer.sh b/examples/industrial_data_pretraining/contextual_paraformer/infer.sh
similarity index 92%
rename from examples/industrial_data_pretraining/neat_contextual_paraformer/infer.sh
rename to examples/industrial_data_pretraining/contextual_paraformer/infer.sh
index 4ae7d03..2dbc627 100644
--- a/examples/industrial_data_pretraining/neat_contextual_paraformer/infer.sh
+++ b/examples/industrial_data_pretraining/contextual_paraformer/infer.sh
@@ -1,6 +1,6 @@
# download model
-local_path_root=./modelscope_models
+local_path_root=../modelscope_models
mkdir -p ${local_path_root}
local_path=${local_path_root}/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404
git clone https://www.modelscope.cn/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404.git ${local_path}
diff --git a/examples/industrial_data_pretraining/neat_contextual_paraformer/demo.py b/examples/industrial_data_pretraining/neat_contextual_paraformer/demo.py
deleted file mode 100644
index b74aacd..0000000
--- a/examples/industrial_data_pretraining/neat_contextual_paraformer/demo.py
+++ /dev/null
@@ -1,12 +0,0 @@
-#!/usr/bin/env python3
-# -*- encoding: utf-8 -*-
-# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
-# MIT License (https://opensource.org/licenses/MIT)
-
-from funasr import AutoModel
-
-model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404")
-
-res = model(input="/Users/zhifu/Downloads/modelscope_models/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/example/asr_example.wav",
- hotword='杈鹃瓟闄� 榄旀惌')
-print(res)
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/demo.py b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
new file mode 100644
index 0000000..0edbb2a
--- /dev/null
+++ b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+# -*- encoding: utf-8 -*-
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
+
+from funasr import AutoModel
+
+model = AutoModel(model="../modelscope_models/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404")
+
+res = model(input="../modelscope_models/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/example/asr_example.wav",
+ hotword='杈鹃瓟闄� 榄旀惌')
+print(res)
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/neat_contextual_paraformer/infer.sh b/examples/industrial_data_pretraining/seaco_paraformer/infer.sh
similarity index 66%
copy from examples/industrial_data_pretraining/neat_contextual_paraformer/infer.sh
copy to examples/industrial_data_pretraining/seaco_paraformer/infer.sh
index 4ae7d03..bfb4315 100644
--- a/examples/industrial_data_pretraining/neat_contextual_paraformer/infer.sh
+++ b/examples/industrial_data_pretraining/seaco_paraformer/infer.sh
@@ -1,9 +1,9 @@
# download model
-local_path_root=./modelscope_models
+local_path_root=../modelscope_models
mkdir -p ${local_path_root}
local_path=${local_path_root}/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404
-git clone https://www.modelscope.cn/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404.git ${local_path}
+git clone https://www.modelscope.cn/damo/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
python funasr/bin/inference.py \
diff --git a/funasr/models/neat_contextual_paraformer/__init__.py b/funasr/models/contextual_paraformer/__init__.py
similarity index 100%
rename from funasr/models/neat_contextual_paraformer/__init__.py
rename to funasr/models/contextual_paraformer/__init__.py
diff --git a/funasr/models/neat_contextual_paraformer/decoder.py b/funasr/models/contextual_paraformer/decoder.py
similarity index 100%
rename from funasr/models/neat_contextual_paraformer/decoder.py
rename to funasr/models/contextual_paraformer/decoder.py
diff --git a/funasr/models/neat_contextual_paraformer/model.py b/funasr/models/contextual_paraformer/model.py
similarity index 98%
rename from funasr/models/neat_contextual_paraformer/model.py
rename to funasr/models/contextual_paraformer/model.py
index 939df31..1bb2d32 100644
--- a/funasr/models/neat_contextual_paraformer/model.py
+++ b/funasr/models/contextual_paraformer/model.py
@@ -55,12 +55,12 @@
from funasr.register import tables
-@tables.register("model_classes", "NeatContextualParaformer")
-class NeatContextualParaformer(Paraformer):
+@tables.register("model_classes", "ContextualParaformer")
+class ContextualParaformer(Paraformer):
"""
Author: Speech Lab of DAMO Academy, Alibaba Group
- Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
- https://arxiv.org/abs/2206.08317
+ FunASR: A Fundamental End-to-End Speech Recognition Toolkit
+ https://arxiv.org/abs/2305.11013
"""
def __init__(
diff --git a/funasr/models/neat_contextual_paraformer/template.yaml b/funasr/models/contextual_paraformer/template.yaml
similarity index 98%
rename from funasr/models/neat_contextual_paraformer/template.yaml
rename to funasr/models/contextual_paraformer/template.yaml
index 6efc62c..fbd15ce 100644
--- a/funasr/models/neat_contextual_paraformer/template.yaml
+++ b/funasr/models/contextual_paraformer/template.yaml
@@ -6,7 +6,7 @@
# tables.print()
# network architecture
-model: NeatContextualParaformer
+model: ContextualParaformer
model_conf:
ctc_weight: 0.0
lsm_weight: 0.1
--
Gitblit v1.9.1