I attempted to compare the results of two different voice samples using the model I trained

[kevin00616]

Describe the bug

I attempted to compare the results of two different voice samples using the model I trained and a pre-trained model from Hugging Face. However, I observed that the results were consistently the same, regardless of the input.

Please help me to fix this problem.

ps.I am not sure if my model was loaded successfully or not.But there were no error messages thrown by the program.

Expected behaviour

I can sucess compare the results.

To Reproduce

from speechbrain.pretrained import SpeakerRecognition
#verification = SpeakerRecognition.from_hparams(source="speechbrain/spkrec-ecapa-voxceleb", savedir="pretrained_models/spkrec-ecapa-voxceleb")
verification = SpeakerRecognition.from_hparams(source="/home/kalvin00616/Desktop/speechbrain/recipes/VoxCeleb/SpeakerRec/results/save/CKPT+2023-10-26+03-21-13+00/CKPT+2023-10-26+03-21-13+00/embedding_model.ckpt", savedir="pretrained_models/spkrec-ecapa-voxceleb")

for a in range(1,4):
file = open('audio_txt/'+str(a)+'_txt','w')
file.close()
for i in range(1,10):
score, prediction = verification.verify_files("test/"+str(a)+".wav", "engaudio/"+str(i)+".wav") # Different Speakers
print((str(a)+","+str(i),score,prediction),file=open('engaudio_txt/test/'+str(a)+'_txt','a'))

Environment Details

No response

Relevant Log Output

No response

Additional Context

No response