speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

add demo.py for all kws models (#2107)

Browse Source 
Co-authored-by: pengteng.spt <pengteng.spt@alibaba-inc.com>
This commit is contained in:
sugarcase 2024-09-25 23:24:58 +08:00 committed by GitHub
parent 8745733b54
commit 8cd8e25f18
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 75 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
examples/industrial_data_pretraining/fsmn_kws/demo.py Normal file
View File

@ -0,0 +1,18 @@
#!/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="iic/speech_charctc_kws_phone-xiaoyun",
keywords="小云小云",
output_dir="./outputs/debug",
device='cpu'
)
test_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/KWS/pos_testset/kws_xiaoyunxiaoyun.wav"
res = model.generate(input=test_wav, cache={},)
print(res)

18
examples/industrial_data_pretraining/fsmn_kws_mt/demo.py Normal file
View File

@ -0,0 +1,18 @@
#!/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="iic/speech_charctc_kws_phone-xiaoyun",
keywords="小云小云",
output_dir="./outputs/debug",
device='cpu'
)
test_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/KWS/pos_testset/kws_xiaoyunxiaoyun.wav"
res = model.generate(input=test_wav, cache={},)
print(res)

18
examples/industrial_data_pretraining/sanm_kws/demo.py Normal file
View File

@ -0,0 +1,18 @@
#!/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="iic/speech_sanm_kws_phone-xiaoyun-commands-offline",
keywords="小云小云",
output_dir="./outputs/debug",
device='cpu'
)
test_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/KWS/pos_testset/kws_xiaoyunxiaoyun.wav"
res = model.generate(input=test_wav, cache={},)
print(res)

21
examples/industrial_data_pretraining/sanm_kws_streaming/demo.py Normal file
View File

@ -0,0 +1,21 @@
#!/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="iic/speech_sanm_kws_phone-xiaoyun-commands-online",
keywords="小云小云",
output_dir="./outputs/debug",
device='cpu',
chunk_size=[4, 8, 4],
encoder_chunk_look_back=0,
decoder_chunk_look_back=0,
)
test_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/KWS/pos_testset/kws_xiaoyunxiaoyun.wav"
res = model.generate(input=test_wav, cache={},)
print(res)