Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
facebook
/
wav2vec2-base-960h
like
387
Follow
AI at Meta
11k
Automatic Speech Recognition
Transformers
PyTorch
google-tensorflow
TensorFlow
Safetensors
librispeech_asr
English
wav2vec2
audio
hf-asr-leaderboard
Eval Results (legacy)
arxiv:
2006.11477
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
17
Deploy
Use this model
main
wav2vec2-base-960h
1.13 GB
8 contributors
History:
37 commits
lysandre
HF Staff
Narsil
Adding `safetensors` variant of this model (
#7
)
22aad52
about 3 years ago
.gitattributes
790 Bytes
Adding `safetensors` variant of this model (#7)
about 3 years ago
README.md
4.43 kB
Remove `soundfile` import (#2)
over 3 years ago
config.json
1.6 kB
add model
over 4 years ago
feature_extractor_config.json
158 Bytes
add feature extractor config"
almost 5 years ago
model.safetensors
378 MB
xet
Adding `safetensors` variant of this model (#7)
about 3 years ago
preprocessor_config.json
159 Bytes
add processor file
almost 5 years ago
pytorch_model.bin
378 MB
xet
upload all files
about 5 years ago
special_tokens_map.json
85 Bytes
upload all files
about 5 years ago
tf_model.h5
378 MB
xet
add model
over 4 years ago
tokenizer_config.json
163 Bytes
Update tokenizer_config.json
almost 5 years ago
vocab.json
291 Bytes
upload all files
about 5 years ago
