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 unit test for speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch

Browse Source
This commit is contained in:
志浩 2023-03-09 14:11:52 +08:00
parent 777ae05adb
commit 3c2ff9b084
2 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
egs_modelscope/speaker_verification/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch/infer.py
View File

@ -11,11 +11,11 @@ if __name__ == '__main__':
# extract speaker embedding
# for url use "spk_embedding" 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')
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/sv_example_enroll.wav')
enroll = rec_result["spk_embedding"]
# for local file use "spk_embedding" as key
rec_result = inference_sv_pipline(audio_in='sv_example_same.wav')["test1"]
rec_result = inference_sv_pipline(audio_in='sv_example_same.wav')
same = rec_result["spk_embedding"]
import soundfile
@ -24,11 +24,11 @@ if __name__ == '__main__':
spk_embedding = inference_sv_pipline(audio_in=wav)["spk_embedding"]
rec_result = inference_sv_pipline(
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_different.wav')
audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/sv_example_different.wav')
different = rec_result["spk_embedding"]
# calculate cosine similarity for same speaker
sv_threshold = 0.9465
sv_threshold = 0.80
same_cos = np.sum(enroll * same) / (np.linalg.norm(enroll) * np.linalg.norm(same))
same_cos = max(same_cos - sv_threshold, 0.0) / (1.0 - sv_threshold) * 100.0
print("Similarity:", same_cos)

8
egs_modelscope/speaker_verification/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch/infer_sv.py
View File

@ -9,13 +9,13 @@ if __name__ == '__main__':
# the same speaker
rec_result = inference_sv_pipline(audio_in=(
'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_enroll.wav',
'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_same.wav'))
'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/sv_example_enroll.wav',
'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/sv_example_same.wav'))
print("Similarity", rec_result["scores"])
# different speakers
rec_result = inference_sv_pipline(audio_in=(
'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_enroll.wav',
'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_different.wav'))
'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/sv_example_enroll.wav',
'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/sv_example_different.wav'))
print("Similarity", rec_result["scores"])