does this also have a problem spelling digits?

from transformers import pipeline
from datasets import load_dataset
import soundfile as sf

synthesiser = pipeline("text-to-speech", "microsoft/speecht5_tts")

embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)

speech = synthesiser("Guten Tag, wie geht's ?!", forward_params={"speaker_embeddings": speaker_embedding})

sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])

a sample code like this would be really great to see