malaysia-ai / xcodec2-25TPS-24k

huggingface.co
Total runs: 127
24-hour runs: 0
7-day runs: 7
30-day runs: 7
Model's Last Updated: November 19 2025
feature-extraction

Introduction of xcodec2-25TPS-24k

Model Details of xcodec2-25TPS-24k

xcodec2-25TPS-24k

Improve https://huggingface.co/HKUSTAudio/xcodec2 from 50 TPS to become 25 TPS and upscale output to 24k sample rate.

WanDB at https://wandb.ai/huseinzol05/xcodec2-24k-25tps , we also pushed all checkpoints in checkpoint .

Dataset
  1. https://huggingface.co/datasets/malaysia-ai/common_voice_17_0 , train set only.
  2. https://huggingface.co/datasets/mesolitica/Malaysian-STT-Whisper-Stage2 , except noise and audioset_0.5s .
  3. https://huggingface.co/datasets/malaysia-ai/Multilingual-TTS , specific commit 2421a13e07226d96ac7009d5327d96a84672768c except cml-tts and libritts_r_filtered
  4. https://huggingface.co/datasets/mesolitica/Malaysian-Emilia-v2 , only sg_podcast and malaysian_podcast
How to
  1. Git clone,
git clone https://github.com/malaysia-ai/X-Codec-2.0-25TPS-24k
cd X-Codec-2.0-25TPS-24k
  1. Load the model,
from modeling_xcodec2 import XCodec2Model
model = XCodec2Model.from_pretrained("malaysia-ai/xcodec2-25TPS-24k")
  1. Encode,
import librosa

y, sr = librosa.load('259041.mp3', sr = 16000)
wav_tensor = torch.from_numpy(y).float().unsqueeze(0)
codes = model.encode_code(wav_tensor)
  1. Decode,
import IPython.display as ipd

ipd.Audio(model.decode_code(codes)[0, 0].cpu(), rate = 24000)
Source code

Source code at https://github.com/malaysia-ai/X-Codec-2.0-25TPS-24k

Runs of malaysia-ai xcodec2-25TPS-24k on huggingface.co

127
Total runs
0
24-hour runs
2
3-day runs
7
7-day runs
7
30-day runs

More Information About xcodec2-25TPS-24k huggingface.co Model

xcodec2-25TPS-24k huggingface.co

xcodec2-25TPS-24k huggingface.co is an AI model on huggingface.co that provides xcodec2-25TPS-24k's model effect (), which can be used instantly with this malaysia-ai xcodec2-25TPS-24k model. huggingface.co supports a free trial of the xcodec2-25TPS-24k model, and also provides paid use of the xcodec2-25TPS-24k. Support call xcodec2-25TPS-24k model through api, including Node.js, Python, http.

xcodec2-25TPS-24k huggingface.co Url

https://huggingface.co/malaysia-ai/xcodec2-25TPS-24k

malaysia-ai xcodec2-25TPS-24k online free

xcodec2-25TPS-24k huggingface.co is an online trial and call api platform, which integrates xcodec2-25TPS-24k's modeling effects, including api services, and provides a free online trial of xcodec2-25TPS-24k, you can try xcodec2-25TPS-24k online for free by clicking the link below.

malaysia-ai xcodec2-25TPS-24k online free url in huggingface.co:

https://huggingface.co/malaysia-ai/xcodec2-25TPS-24k

xcodec2-25TPS-24k install

xcodec2-25TPS-24k is an open source model from GitHub that offers a free installation service, and any user can find xcodec2-25TPS-24k on GitHub to install. At the same time, huggingface.co provides the effect of xcodec2-25TPS-24k install, users can directly use xcodec2-25TPS-24k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

xcodec2-25TPS-24k install url in huggingface.co:

https://huggingface.co/malaysia-ai/xcodec2-25TPS-24k

Url of xcodec2-25TPS-24k

xcodec2-25TPS-24k huggingface.co Url

Provider of xcodec2-25TPS-24k huggingface.co

malaysia-ai
ORGANIZATIONS

Other API from malaysia-ai