unispeech-sat-base-sv

from transformers import Wav2Vec2FeatureExtractor, UniSpeechSatForXVector
from datasets import load_dataset
import torch

dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")

feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained('microsoft/unispeech-sat-base-sv')
model = UniSpeechSatForXVector.from_pretrained('microsoft/unispeech-sat-base-sv')

# audio files are decoded on the fly
inputs = feature_extractor(dataset[:2]["audio"]["array"], return_tensors="pt")
embeddings = model(**inputs).embeddings
embeddings = torch.nn.functional.normalize(embeddings, dim=-1).cpu()

# the resulting embeddings can be used for cosine similarity-based retrieval
cosine_sim = torch.nn.CosineSimilarity(dim=-1)
similarity = cosine_sim(embeddings[0], embeddings[1])
threshold = 0.86  # the optimal threshold is dataset-dependent
if similarity < threshold:
    print("Speakers are not the same!")