Update app.py

app.py

@@ -4,7 +4,7 @@ import torch
 from datasets import load_dataset
 
 from transformers import SpeechT5ForTextToSpeech, SpeechT5HifiGan, SpeechT5Processor, pipeline
-
+from speechbrain.pretrained import EncoderClassifier
 
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 
@@ -25,6 +25,23 @@ vocoder = SpeechT5HifiGan.from_pretrained("sanchit-gandhi/speecht5_tts_vox_nl").
 # embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
 # speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
 
+spk_model_name = "speechbrain/spkrec-xvect-voxceleb"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+speaker_model = EncoderClassifier.from_hparams(
+    source=spk_model_name,
+    run_opts={"device": device},
+    savedir=os.path.join("/tmp", spk_model_name),
+)
+
+def create_speaker_embedding(waveform):
+    with torch.no_grad():
+        speaker_embeddings = speaker_model.encode_batch(torch.tensor(waveform))
+        speaker_embeddings = torch.nn.functional.normalize(speaker_embeddings, dim=2)
+        speaker_embeddings = speaker_embeddings.squeeze().cpu().numpy()
+    return speaker_embeddings
+
+
 dataset_nl = load_dataset("facebook/voxpopuli", "nl", split="train", streaming=True)
 data_list = []
 speaker_embeddings_list = []