Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Finnish-NLP
/
wav2vec2-large-uralic-voxpopuli-v2-finnish
like
0
Follow
Finnish-NLP
45
Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
mozilla-foundation/common_voice_9_0
Finnish
wav2vec2
finnish
Generated from Trainer
hf-asr-leaderboard
Eval Results
Inference Endpoints
arxiv:
2006.11477
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
1
Train
Deploy
Use this model
refs/pr/1
wav2vec2-large-uralic-voxpopuli-v2-finnish
1 contributor
History:
69 commits
SFconvertbot
Adding `safetensors` variant of this model
e687b41
verified
30 days ago
language_model
Upload lm-boosted decoder
over 2 years ago
runs
End of training
over 2 years ago
.gitattributes
1.29 kB
Adding `safetensors` variant of this model
30 days ago
.gitignore
13 Bytes
Training in progress, step 500
over 2 years ago
README.md
16.2 kB
Update README.md
over 2 years ago
added_tokens.json
23 Bytes
add tokenizer
over 2 years ago
alphabet.json
223 Bytes
Upload lm-boosted decoder
over 2 years ago
config.json
2.33 kB
Training in progress, step 500
over 2 years ago
eval.py
5.37 kB
Upload eval.py
over 2 years ago
model.safetensors
1.26 GB
LFS
Adding `safetensors` variant of this model
30 days ago
preprocessor_config.json
262 Bytes
Upload lm-boosted decoder
over 2 years ago
pytorch_model.bin
1.26 GB
LFS
End of training
over 2 years ago
run-finnish-asr-models.ipynb
22.1 kB
Upload run-finnish-asr-models.ipynb
over 2 years ago
special_tokens_map.json
502 Bytes
Upload lm-boosted decoder
over 2 years ago
tokenizer_config.json
373 Bytes
Upload lm-boosted decoder
over 2 years ago
training_args.bin
pickle
Detected Pickle imports (6)
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.TrainingArguments"
,
"transformers.trainer_utils.HubStrategy"
,
"torch.device"
How to fix it?
3.31 kB
LFS
Training in progress, step 500
over 2 years ago
vocab.json
289 Bytes
add tokenizer
over 2 years ago