elgeish
/

wav2vec2-large-xlsr-53-arabic

Automatic Speech Recognition

xlsr-fine-tuning-week

hf-asr-leaderboard

Inference Endpoints

Model card Files Files and versions Community

wav2vec2-large-xlsr-53-arabic

3 contributors

History: 10 commits

elgeish's picture

use torchaudio (faster than librosa)

e904c32 over 3 years ago

.gitattributes

690 Bytes

initial commit almost 4 years ago
README.md

6.54 kB

use torchaudio (faster than librosa) over 3 years ago
config.json

1.35 kB

update model and vocab almost 4 years ago
preprocessor_config.json

159 Bytes

upload files almost 4 years ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
1.26 GB
LFS

uploading common-voice model over 3 years ago
special_tokens_map.json

85 Bytes

upload files almost 4 years ago
tokenizer_config.json

303 Bytes

update model and vocab almost 4 years ago
vocab.json

507 Bytes

update model and vocab almost 4 years ago