funasr1.0 paraformer_streaming

游雁

2024-01-11 487420b1b54dd20f8dc114fc3ddf7616ce035b4c

funasr1.0 paraformer_streaming

 examples/industrial_data_pretraining/campplus_sv/demo.py

 examples/industrial_data_pretraining/paraformer-zh/__init__.py

 examples/industrial_data_pretraining/paraformer-zh/demo.py

New file
@@ -0,0 +1,20 @@
#!/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="damo/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
                  model_revision="v2.0.0",
                  vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
                  vad_model_revision="v2.0.0",
                  punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
                  punc_model_revision="v2.0.0",
                  spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
                  spk_model_revision="v2.0.0"
                  )

res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
            hotword='达摩院 磨搭')
print(res)

 examples/industrial_data_pretraining/paraformer-zh/infer.sh

New file
@@ -0,0 +1,19 @@

model="damo/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model_revision="v2.0.0"
vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
vad_model_revision="v2.0.0"
punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
punc_model_revision="v2.0.0"

python funasr/bin/inference.py \
+model=${model} \
+model_revision=${model_revision} \
+vad_model=${vad_model} \
+vad_model_revision=${vad_model_revision} \
+punc_model=${punc_model} \
+punc_model_revision=${punc_model_revision} \
+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
+output_dir="./outputs/debug" \
+device="cpu" \
+"hotword='达摩院 魔搭'"