uv pip install transformers torch torchaudio einops

import torch
import torchaudio
from transformers import AutoModel

# Load the model
model = AutoModel.from_pretrained("mispeech/dashengtokenizer", trust_remote_code=True)
model.eval()

# Load audio file (only 16kHz supported!)
audio, sr = torchaudio.load("path/to/audio.wav")

# Optional: Create attention mask for variable-length inputs
# attention_mask = torch.ones(audio.shape[0], audio.shape[1])  # All ones for full audio
# attention_mask[0, 8000:] = 0  # Example: mask second half of first sample

# Method 1: End-to-end processing (encode + decode)
with torch.no_grad(), torch.autocast(device_type='cuda'):
    outputs = model(audio)  # Optionally pass attention_mask=attention_mask
    reconstructed_audio = outputs["audio"]
    embeddings = outputs['embeddings']

# Method 2: Separate encoding and decoding
with torch.no_grad(), torch.autocast(device_type='cuda'):
    # Encode audio to embeddings
    embeddings = model.encode(audio)  # Optionally pass attention_mask=attention_mask

    # Decode embeddings back to audio
    reconstructed_audio = model.decode(embeddings)

# Save reconstructed audio
torchaudio.save("reconstructed_audio.wav", reconstructed_audio, sr)

embeddings = model.encode(audio)
reconstructed = model.decode(embeddings)

# Extract rich audio features for downstream tasks
features = model.encode(audio)
# Use features for classification, clustering, etc.

@misc{dinkel_dashengtokenizer_2026,
  title={DashengTokenizer: One layer is enough for unified audio understanding and generation},
  author={MiLM Plus, Xiaomi},
  year={2026},
  url={https://huggingface.co/mispeech/dashengtokenizer}
}