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

modify infer.py

Browse Source
This commit is contained in:
志浩 2023-03-03 10:45:10 +08:00
parent 051c876ed8
commit 31dda90f2d
1 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
egs_modelscope/speaker_verification/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/infer.py
View File

@ -9,17 +9,23 @@ if __name__ == '__main__':
)
# 提取不同句子的说话人嵌入码
# for url use "utt_id" as key
rec_result = inference_sv_pipline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_enroll.wav')
enroll = rec_result["spk_embedding"]
enroll = rec_result["utt_id"]
rec_result = inference_sv_pipline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_same.wav')
same = rec_result["spk_embedding"]
# for local file use "utt_id" as key
rec_result = inference_sv_pipline(audio_in='sv_example_same.wav')["test1"]
same = rec_result["test1"]
import soundfile
wav = soundfile.read('sv_example_enroll.wav')[0]
# for raw inputs use "utt_id" as key
spk_embedding = inference_sv_pipline(audio_in=wav)["utt_id"]
rec_result = inference_sv_pipline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_different.wav')
different = rec_result["spk_embedding"]
different = rec_result["utt_id"]
# 对相同的说话人计算余弦相似度
sv_threshold = 0.9465