!pip install torchcodec

Requirement already satisfied: torchcodec in /usr/local/lib/python3.12/dist-packages (0.6.0)

from datasets import load_dataset, Audio
from transformers import MimiModel, AutoFeatureExtractor

model = MimiModel.from_pretrained("kyutai/mimi")
feature_extractor = AutoFeatureExtractor.from_pretrained("kyutai/mimi")

/usr/local/lib/python3.12/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: 
The secret `HF_TOKEN` does not exist in your Colab secrets.
To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.
You will be able to reuse this secret in all of your notebooks.
Please note that authentication is recommended but still optional to access public models or datasets.
  warnings.warn(

librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")

# cast the audio data to the correct sampling rate for the model
librispeech_dummy = librispeech_dummy.cast_column("audio", Audio(sampling_rate=feature_extractor.sampling_rate))
audio_sample = librispeech_dummy[0]["audio"]["array"]

# pre-process the inputs
inputs = feature_extractor(raw_audio=audio_sample, sampling_rate=feature_extractor.sampling_rate, return_tensors="pt")

# explicitly encode then decode the audio inputs
encoder_outputs = model.encode(inputs["input_values"])
audio_values = model.decode(encoder_outputs.audio_codes)[0]

# or the equivalent with a forward pass
audio_values = model(inputs["input_values"]).audio_values

audio_values.shape

torch.Size([1, 1, 140520])