import soundfile as sf
import torch
from transformers import AutoModel

device = "cuda" if torch.cuda.is_available() else "cpu"
wav, sr = sf.read("audio.wav", dtype="float32")
wav = torch.from_numpy(wav)
model = AutoModel.from_pretrained(
    "prj-beatrice/utmos22-torch-native", trust_remote_code=True
).eval().to(device)

with torch.inference_mode():
    score = model(wav.to(device), sampling_rate=sr).scores[0]
print(score)

The result matches this code:

python

reference_model = torch.hub.load(
    "tarepan/SpeechMOS:v1.2.0", "utmos22_strong", trust_repo=True
)
reference = reference_model(wav.unsqueeze(0), sr)[0]
torch.testing.assert_close(score.cpu(), reference)

Padded batches use a waveform tensor [batch_size, max_length] and an input_lengths tensor [batch_size].

License

The model and wrapper are MIT-licensed; see LICENSE.