Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
speechbrain
/
asr-wav2vec2-commonvoice-14-pt
like
2
Follow
SpeechBrain
244
Automatic Speech Recognition
speechbrain
PyTorch
commonvoice.14.0
Portuguese
wav2vec2
CTC
Transformer
Eval Results
arxiv:
2106.04624
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
24e8462
asr-wav2vec2-commonvoice-14-pt
3 contributors
History:
6 commits
poonehmousavi
Rename 1000_unigram.model to tokenizer.ckpt
24e8462
over 1 year ago
.gitattributes
1.52 kB
initial commit
over 1 year ago
README.md
4.68 kB
Upload 4 files
over 1 year ago
common_voice_pt_19287123.mp3
21.2 kB
Upload common_voice_pt_19287123.mp3
over 1 year ago
config.json
1.51 kB
Upload 4 files
over 1 year ago
hyperparams.yaml
2.47 kB
Upload 4 files
over 1 year ago
model.ckpt
pickle
Detected Pickle imports (4)
"torch._utils._rebuild_tensor_v2"
,
"torch.LongStorage"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
16.8 MB
LFS
Upload 2 files
over 1 year ago
preprocessor_config.json
169 Bytes
Upload 4 files
over 1 year ago
tokenizer.ckpt
253 kB
LFS
Rename 1000_unigram.model to tokenizer.ckpt
over 1 year ago
wav2vec2.ckpt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
1.26 GB
LFS
Upload 2 files
over 1 year ago