System Info

• transformers version: 4.46.3
• Platform: Linux-6.6.20-aufs-1-x86_64-with-glibc2.36
• Python version: 3.11.2
• Huggingface_hub version: 0.26.1
• Safetensors version: 0.4.5
• Accelerate version: 1.0.1
• Accelerate config: not found
• PyTorch version (GPU?): 2.5.1+cu124 (True)
• Tensorflow version (GPU?): not installed (NA)
• Flax version (CPU?/GPU?/TPU?): not installed (NA)
• Jax version: not installed
• JaxLib version: not installed
• Using distributed or parallel set-up in script?: No
• Using GPU in script?: Yes
• GPU type: NVIDIA A10

Who can help?

@ylacombe @eustlb

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

import torchaudio
from transformers import MimiModel, AutoFeatureExtractor
model = MimiModel.from_pretrained("kyutai/mimi", num_quantizers=8)
feature_extractor = AutoFeatureExtractor.from_pretrained("kyutai/mimi")
model.cuda()
# load some audio file
inputs = feature_extractor(raw_audio=[audio.squeeze(0).numpy(),audio.squeeze(0).numpy()] , sampling_rate=feature_extractor.sampling_rate, return_tensors="pt")
inputs = {key:value.cuda() for key,value in inputs.items()}
out_batch = model.encode(**inputs).audio_codes
inputs = feature_extractor(raw_audio=audio.squeeze(0).numpy(), sampling_rate=feature_extractor.sampling_rate, return_tensors="pt")
inputs = {key:value.cuda() for key,value in inputs.items()}
out = model.encode(**inputs).audio_codes
(out_batch[0] == out[0]).all() # prints tensor(False, device='cuda:0')

Expected behavior

the output for out_batch[0] and out[0] should be the same.