# Unsupervised Pretraining

Sam2 Hiera Base Plus.fb R896
Apache-2.0
SAM2 model based on the HieraDet image encoder, focused on image feature extraction tasks.
Image Segmentation Transformers
S
timm
764
0
C RADIO
Other
A visual feature extraction model developed by NVIDIA for generating image embeddings, supporting downstream tasks such as image classification.
Transformers
C
nvidia
398
14
Esm1b T33 650M UR50S
MIT
ESM-1b is a Transformer-based protein language model trained via unsupervised learning on protein sequence data, capable of predicting protein structure and function.
Protein Model Transformers
E
facebook
24.20k
18
Assignment1 Omar
Apache-2.0
Wav2Vec2 is a self-supervised learning-based speech recognition model, pre-trained and fine-tuned on 960 hours of LibriSpeech audio data, supporting English speech transcription.
Speech Recognition Transformers English
A
Classroom-workshop
28
0
Response Quality Classifier Large
MIT
This model is used to evaluate the relevance and specificity of the last message in a dialogue, based on the sberbank-ai/ruRoberta-large architecture.
Dialogue System Transformers Other
R
t-bank-ai
33
11
Wav2vec2 Base Nl Voxpopuli
A Wav2Vec2 base model pretrained on the Dutch subset of the VoxPopuli corpus, suitable for Dutch speech recognition tasks.
Speech Recognition Transformers Other
W
facebook
31
0
Viwav2vec2 Base 100h
Apache-2.0
A base Wav2Vec2 model pretrained on 100 hours of unlabeled Vietnamese speech audio from the VLSP dataset, requiring fine-tuning for downstream tasks.
Speech Recognition Transformers Other
V
dragonSwing
19
0
T5 V1 1 Base
Apache-2.0
T5 1.1 is Google's improved text-to-text transfer model, utilizing the GEGLU activation function and optimized architecture, focused on unsupervised pretraining
Large Language Model English
T
google
150.73k
58
T5 V1 1 Xl
Apache-2.0
T5 1.1 is Google's improved text-to-text transfer Transformer model, utilizing GEGLU activation function and optimized architecture, pretrained solely on the C4 dataset in an unsupervised manner
Large Language Model Transformers English
T
google
30.17k
15
Wav2vec2 Large Fr Voxpopuli
A large-scale speech recognition model pretrained on the VoxPopuli French corpus, supporting French speech-to-text tasks
Speech Recognition French
W
facebook
31
0
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase