Audio Classification
Transformers
English
speaker-diarization
streaming
open-speaker
clustering
e-means
Instructions to use Kyudan/eDIAR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kyudan/eDIAR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="Kyudan/eDIAR")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Kyudan/eDIAR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 736 Bytes
1c68fa2 | 1 2 3 4 5 6 7 8 9 10 11 | This repository contains code only; it stores no model weights.
Third-party code included (with its own license):
- emeans_diar/faiss_e_means/ e-means from facebookresearch/faiss contrib/e_means (commit 7767c6396381c6586aba873fda72eec8d6819b7b), MIT license, (c) Meta Platforms, Inc. and affiliates.
- emeans_diar/nemotron_ref/ Nemotron-3 Diarization modeling/processing code, Apache License 2.0, (c) The HuggingFace Inc. team.
- emeans_diar/wespeaker_resnet.py, pooling_layers.py from WeSpeaker, Apache License 2.0, (c) Shuai Wang et al.
Models used at run time, downloaded from their own repositories and subject to their own licenses:
- nvidia/Nemotron-3-Diarization (openmdw-1.1)
- Wespeaker/wespeaker-voxceleb-resnet34-LM
|