AI/EXPLORER
ToolsCategoriesSitesLLMsCompareAI QuizAlternativesPremium
—AI Tools
—Sites & Blogs
—LLMs & Models
—Categories
AI Explorer

Find and compare the best artificial intelligence tools for your projects.

Made within France

Explore

  • ›All tools
  • ›Sites & Blogs
  • ›LLMs & Models
  • ›Compare
  • ›Chatbots
  • ›AI Images
  • ›Code & Dev

Company

  • ›Premium
  • ›About
  • ›Contact
  • ›Blog

Legal

  • ›Legal notice
  • ›Privacy
  • ›Terms

© 2026 AI Explorer·All rights reserved.

HomeLLMsxcodec hubert general

xcodec hubert general

by hf-audio

Open source · 15k downloads · 0 likes

0.0
(0 reviews)EmbeddingAPI & Local
About

X-Codec Hubert General is an audio codec model designed to compress and decompress audio signals with optimal quality, even at very low bitrates (down to 0.5 kbps). It belongs to the X-Codec family and stands out for its ability to preserve the essential characteristics of voice and sound while significantly reducing file sizes. This model is particularly well-suited for applications requiring efficient audio transmission or storage, such as real-time communications or streaming platforms. Its robustness and versatility make it an ideal tool for developers and researchers working on advanced audio projects.

Documentation

X-Codec (general audio)

This codec is part of the X-Codec family of codecs as shown below:

Model checkpointSemantic ModelDomainTraining Data
xcodec-hubert-librispeechfacebook/hubert-base-ls960SpeechLibrispeech
xcodec-wavlm-mlsmicrosoft/wavlm-base-plusSpeechMLS English
xcodec-wavlm-more-datamicrosoft/wavlm-base-plusSpeechMLS English + Internal data
xcodec-hubert-general (this model)ZhenYe234/hubert_base_general_audioGeneral audio200k hours internal data
xcodec-hubert-general-balancedZhenYe234/hubert_base_general_audioGeneral audioMore balanced data

Original model is xcodec_hubert_general_audio from this table.

Example usage

The example below applies the codec over all possible bandwidths.

Python

from datasets import Audio, load_dataset
from transformers import XcodecModel, AutoFeatureExtractor
import torch
import os
from scipy.io.wavfile import write as write_wav


model_id = "hf-audio/xcodec-hubert-general"
torch_device = "cuda" if torch.cuda.is_available() else "cpu"
available_bandwidths = [0.5, 1, 1.5, 2, 4]

# load model
model = XcodecModel.from_pretrained(model_id, device_map=torch_device)
feature_extractor = AutoFeatureExtractor.from_pretrained(model_id)

# load audio example
librispeech_dummy = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
librispeech_dummy = librispeech_dummy.cast_column(
    "audio", Audio(sampling_rate=feature_extractor.sampling_rate)
)
audio_array = librispeech_dummy[0]["audio"]["array"]
inputs = feature_extractor(
    raw_audio=audio_array, sampling_rate=feature_extractor.sampling_rate, return_tensors="pt"
).to(model.device)
audio = inputs["input_values"]

for bandwidth in available_bandwidths:
    print(f"Encoding with bandwidth: {bandwidth} kbps")
    # encode
    audio_codes = model.encode(audio, bandwidth=bandwidth, return_dict=False)
    print("Codebook shape", audio_codes.shape)
    # 0.5 kbps -> torch.Size([1, 1, 293])
    # 1.0 kbps -> torch.Size([1, 2, 293])
    # 1.5 kbps -> torch.Size([1, 3, 293])
    # 2.0 kbps -> torch.Size([1, 4, 293])
    # 4.0 kbps -> torch.Size([1, 8, 293])

    # decode
    input_values_dec = model.decode(audio_codes).audio_values

    # save audio to file
    write_wav(f"{os.path.basename(model_id)}_{bandwidth}.wav", feature_extractor.sampling_rate, input_values_dec.squeeze().detach().cpu().numpy())

write_wav("original.wav", feature_extractor.sampling_rate, audio.squeeze().detach().cpu().numpy())

🔊 Audio Samples

Original

0.5 kbps

1 kbps

1.5 kbps

2 kbps

4 kbps

Batch example

Python

from datasets import Audio, load_dataset
from transformers import XcodecModel, AutoFeatureExtractor
import torch


model_id = "hf-audio/xcodec-hubert-general"
torch_device = "cuda" if torch.cuda.is_available() else "cpu"
bandwidth = 4
n_audio = 2  # number of audio samples to process in a batch

# load model
model = XcodecModel.from_pretrained(model_id, device_map=torch_device)
feature_extractor = AutoFeatureExtractor.from_pretrained(model_id)

# load audio example
ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
ds = ds.cast_column(
    "audio", Audio(sampling_rate=feature_extractor.sampling_rate)
)
audio = [audio_sample["array"] for audio_sample in ds[-n_audio:]["audio"]]
print(f"Input audio shape: {[_sample.shape for _sample in audio]}")
# Input audio shape: [(113840,), (71680,)]
inputs = feature_extractor(
    raw_audio=audio, sampling_rate=feature_extractor.sampling_rate, return_tensors="pt"
).to(model.device)
audio = inputs["input_values"]
print(f"Padded audio shape: {audio.shape}")
# Padded audio shape: torch.Size([2, 1, 113920])

# encode
audio_codes = model.encode(audio, bandwidth=bandwidth, return_dict=False)
print("Codebook shape", audio_codes.shape)
# Codebook shape torch.Size([2, 8, 356])

# decode
decoded_audio = model.decode(audio_codes).audio_values
print("Decoded audio shape", decoded_audio.shape)
# Decoded audio shape torch.Size([2, 1, 113920])
Capabilities & Tags
transformerssafetensorsxcodecfeature-extractionendpoints_compatible
Links & Resources
Specifications
CategoryEmbedding
AccessAPI & Local
LicenseOpen Source
PricingOpen Source
Rating
0.0

Try xcodec hubert general

Access the model directly