Instructions to use Scicom-intl/xcodec2-25TPS-24k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Scicom-intl/xcodec2-25TPS-24k with Transformers:
# Load model directly from transformers import AutoFeatureExtractor, AutoModel extractor = AutoFeatureExtractor.from_pretrained("Scicom-intl/xcodec2-25TPS-24k", trust_remote_code=True) model = AutoModel.from_pretrained("Scicom-intl/xcodec2-25TPS-24k", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag and link to paper
#1
by nielsr HF Staff - opened
This PR improves the model card by:
- Adding the
audio-to-audiopipeline tag to the metadata for better discoverability. - Linking the model to its associated research paper: Improving X-Codec-2.0 for Multi-Lingual Speech: 25 Hz Latent Rate and 24 kHz Sampling.
- Adding a missing
import torchto the sample usage code snippet.
huseinzolkepliscicom changed pull request status to merged