facebook
/

wav2vec2-base-960h

Automatic Speech Recognition PyTorch TensorFlow Safetensors Transformers

wav2vec2 audio hf-asr-leaderboard Eval Results License: apache-2.0

Model card Files Files and versions Community

wav2vec2-base-960h

8 contributors

History: 37 commits

lysandre's picture

HF staff

Narsil's picture

HF staff

Adding `safetensors` variant of this model (#7)

22aad52 2 months ago

.gitattributes

790 Bytes Adding `safetensors` variant of this model (#7) 2 months ago
README.md

4.43 kB Remove `soundfile` import (#2) 7 months ago
config.json

1.6 kB add model over 1 year ago
feature_extractor_config.json

158 Bytes add feature extractor config" almost 2 years ago
model.safetensors

378 MB
LFS
Adding `safetensors` variant of this model (#7) 2 months ago
preprocessor_config.json

159 Bytes add processor file almost 2 years ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.FloatStorage"
What is a pickle import?
378 MB
LFS
upload all files almost 2 years ago
special_tokens_map.json

85 Bytes upload all files almost 2 years ago
tf_model.h5

378 MB
LFS
add model over 1 year ago
tokenizer_config.json

163 Bytes Update tokenizer_config.json almost 2 years ago
vocab.json

291 Bytes upload all files almost 2 years ago