Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
enactic
/
avista-base
like
1
Follow
Enactic, Inc.
8
Automatic Speech Recognition
Transformers
PyTorch
Japanese
avhubert
AVSR
AVHuBERT
custom_code
arxiv:
2201.02184
arxiv:
2201.01763
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
refs/pr/1
avista-base
1.31 GB
1 contributor
History:
6 commits
SFconvertbot
Adding `safetensors` variant of this model
9d59d62
verified
27 days ago
.gitattributes
1.52 kB
initial commit
about 2 months ago
README.md
7.41 kB
Update README.md
about 1 month ago
config.json
141 kB
Upload AVHubertForConditionalGeneration
about 2 months ago
configuration_avhubert.py
6.63 kB
Upload AVHubertForConditionalGeneration
about 2 months ago
configuration_resnet.py
409 Bytes
Upload AVHubertForConditionalGeneration
about 2 months ago
decoder.py
47.7 kB
Upload AVHubertForConditionalGeneration
about 2 months ago
feature_extraction_avhubert.py
10.3 kB
Upload processor
about 2 months ago
generation_config.json
141 Bytes
Upload AVHubertForConditionalGeneration
about 2 months ago
model.safetensors
653 MB
xet
Adding `safetensors` variant of this model
27 days ago
modeling_avhubert.py
16.5 kB
Upload AVHubertForConditionalGeneration
about 2 months ago
modeling_resnet.py
5.6 kB
Upload AVHubertForConditionalGeneration
about 2 months ago
preprocessor_config.json
1.05 kB
Upload processor
about 2 months ago
processing_avhubert.py
5.06 kB
Upload processor
about 2 months ago
processor_config.json
127 Bytes
Upload processor
about 2 months ago
pytorch_model.bin
653 MB
xet
Upload AVHubertForConditionalGeneration
about 2 months ago
special_tokens_map.json
552 Bytes
Upload processor
about 2 months ago
tokenizer.json
507 kB
Upload processor
about 2 months ago
tokenizer_config.json
1.13 kB
Upload processor
about 2 months ago