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 infer test for sond models

Browse Source
This commit is contained in:
志浩 2023-04-07 19:01:41 +08:00
parent 917162a9a7
commit 0e3b3e0482
2 changed files with 29 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py → egs_modelscope/speaker_diarization/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch/infer.py
View File

@ -14,13 +14,12 @@ inference_diar_pipline = pipeline(
)
# 以 audio_list 作为输入，其中第一个音频为待检测语音，后面的音频为不同说话人的声纹注册语音
audio_list = [[
audio_list = [
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/record.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_A.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B1.wav"
]]
]
results = inference_diar_pipline(audio_in=audio_list)
for rst in results:
print(rst["value"])
print(results)

26
egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/infer.py Normal file
View File

@ -0,0 +1,26 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
# 初始化推理 pipeline
# 当以原始音频作为输入时使用配置文件 sond.yaml，并设置 mode 为sond_demo
inference_diar_pipline = pipeline(
mode="sond_demo",
num_workers=0,
task=Tasks.speaker_diarization,
diar_model_config="sond.yaml",
model='damo/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch',
sv_model="damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch",
sv_model_revision="master",
)
# 以 audio_list 作为输入，其中第一个音频为待检测语音，后面的音频为不同说话人的声纹注册语音
audio_list = [
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/record.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/spk1.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/spk2.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/spk3.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/speaker_diarization/spk4.wav",
]
results = inference_diar_pipline(audio_in=audio_list)
print(results)