Downloads · 30 days
0
wav2vec2-vietnamese-kmeans-16384
giangndm/wav2vec2-vietnamese-kmeans-16384
wav2vec2-vietnamese-kmeans-16384 is a machine learning model from giangndm. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains the 16,384 trained FAISS K-Means centroids used to discretize continuous speech representations from the nguyenvulebinh/wav2vec2-base-vietnamese-250h model.
Access
Public
Updated Jul 16, 2026
Repo size
50.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.npy50.3 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026
- SHA
- b6ff9b2e
Model card
From the Hugging Face model README
Vietnamese Wav2Vec2 K-Means Codebook (16,384 Centroids)
This repository contains the 16,384 trained FAISS K-Means centroids used to discretize continuous speech representations from the nguyenvulebinh/wav2vec2-base-vietnamese-250h model.
📊 Model Details
- Base Backbone: Wav2Vec2 Base Vietnamese 250h.
- Cluster Count (K): 16,384 centroids (768-dimensional float32 vectors).
- Training Source: Fitted on 2.6 Million speech frames from both
audio-pw733-rawandviVoicedatasets.
🔗 Linked Dataset
The tokenized feature dataset generated using this codebook is hosted at: 👉 giangndm/audio-confidence-alignment
🚀 How to Load
import numpy as np
import faiss
# Load centroids
centroids = np.load("kmeans_faiss_16384_centroids.npy")
print(f"Centroids shape: {centroids.shape}") # [16384, 768]
# Build FAISS index for fast search
index = faiss.IndexFlatL2(768)
index.add(centroids)
Developed as part of the Multi-Project Voice Research Spike under rd-lumi/luvox-vibe-research.
- License
- mit
- Languages
- vi
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026