Merge branch 'dev_gzf_funasr2' of github.com:alibaba-damo-academy/FunASR into dev_gzf_funasr2

add

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='达魔院 魔搭')
+print(res)

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}

examples/industrial_data_pretraining/neat_contextual_paraformer/demo.py

@@ -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='达魔院 魔搭')
-print(res)

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='达魔院 魔搭')
+print(res)

examples/industrial_data_pretraining/seaco_paraformer/infer.sh

@@ -0,0 +1,15 @@
+
+# download model
+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_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
+
+
+python funasr/bin/inference.py \
++model="${local_path}" \
++input="${local_path}/example/asr_example.wav" \
++output_dir="./outputs/debug" \
++device="cpu" \
++"hotword='达魔院 魔搭'"
+

funasr/models/contextual_paraformer/model.py

@@ -55,12 +55,12 @@ from funasr.models.paraformer.model import Paraformer
 
 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__(

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