Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Edresson
/
wav2vec2-large-100k-voxpopuli-ft-Common_Voice_plus_TTS-Dataset_plus_Data_Augmentation-russian
like
2
Automatic Speech Recognition
Transformers
PyTorch
Portuguese
wav2vec2
audio
speech
Russian-speech-corpus
PyTorch
Eval Results
Inference Endpoints
arxiv:
2204.00618
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
981996c
wav2vec2-large-100k-voxpopuli-ft-Common_Voice_plus_TTS-Dataset_plus_Data_Augmentation-russian
/
train_results.json
Edresson
Add checkpoints
981996c
almost 3 years ago
raw
Copy download link
history
blame
Safe
122 Bytes
{
"epoch"
:
73.0
,
"train_runtime"
:
465541.7438
,
"train_samples"
:
81775
,
"train_samples_per_second"
:
0.091
}