huggingface--transformers/docs/source/en/model_doc/mimi.md

This model was contributed to Hugging Face Transformers on 2024-09-18.

Mimi

Mimi is a neural audio codec model with pretrained and quantized variants, designed for efficient speech representation and compression. The model operates at 1.1 kbps with a 12 Hz frame rate and uses a convolutional encoder-decoder architecture combined with a residual vector quantizer of 16 codebooks. Mimi outputs dual token streams i.e. semantic and acoustic to balance linguistic richness with high fidelity reconstruction. Key features include a causal streaming encoder for low-latency use, dual-path tokenization for flexible downstream generation, and integration readiness with large speech models like Moshi.

You can find the original Mimi checkpoints under the Kyutai organization.

Tip

This model was contributed by ylacombe.

Click on the Mimi models in the right sidebar for more examples of how to apply Mimi.

The example below demonstrates how to encode and decode audio with the [AutoModel] class.

from datasets import Audio, load_dataset

from transformers import AutoFeatureExtractor, MimiModel


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

# load model and feature extractor
model = MimiModel.from_pretrained("kyutai/mimi", device_map="auto")
feature_extractor = AutoFeatureExtractor.from_pretrained("kyutai/mimi")

# load audio sample
librispeech_dummy = librispeech_dummy.cast_column("audio", Audio(sampling_rate=feature_extractor.sampling_rate))
audio_sample = librispeech_dummy[-1]["audio"]["array"]
inputs = feature_extractor(raw_audio=audio_sample, sampling_rate=feature_extractor.sampling_rate, return_tensors="pt").to(model.device)

encoder_outputs = model.encode(inputs["input_values"], inputs["padding_mask"])
audio_values = model.decode(encoder_outputs.audio_codes, inputs["padding_mask"])[0]
# or the equivalent with a forward pass
audio_values = model(inputs["input_values"], inputs["padding_mask"]).audio_values

MimiConfig

autodoc MimiConfig

MimiModel

autodoc MimiModel - decode - encode - forward